{"id":"https://openalex.org/W7225261646","doi":"https://doi.org/10.48550/arxiv.2611.04106","title":"Structure, Dimensionality, and Distribution Shape - What Makes Pretraining Data Transferable, and Why the Input Pipeline Decides Which","display_name":"Structure, Dimensionality, and Distribution Shape - What Makes Pretraining Data Transferable, and Why the Input Pipeline Decides Which","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225261646","doi":"https://doi.org/10.48550/arxiv.2611.04106"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.04106","doi":"https://doi.org/10.48550/arxiv.2611.04106","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04106","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.04106","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110968694","display_name":"Sangyoon Bae","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bae, Sangyoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033979262","display_name":"Jiook Cha","orcid":"https://orcid.org/0000-0002-5314-7992","observed_orcids":["https://orcid.org/0000-0002-5314-7992"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cha, Jiook","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5228999853134155,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.5228999853134155,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.26759999990463257,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.05000000074505806,"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/data-transferability","display_name":"data transferability","score":0.7559999823570251},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.5460000038146973},{"id":"https://openalex.org/keywords/data-structures","display_name":"data structures","score":0.5249999761581421},{"id":"https://openalex.org/keywords/dimensionality","display_name":"dimensionality","score":0.7670000195503235},{"id":"https://openalex.org/keywords/distribution-shape","display_name":"distribution shape","score":0.9229999780654907},{"id":"https://openalex.org/keywords/input-normalization","display_name":"input normalization","score":0.6520000100135803},{"id":"https://openalex.org/keywords/patchtst","display_name":"PatchTST","score":0.8270000219345093},{"id":"https://openalex.org/keywords/chronos","display_name":"Chronos","score":0.8220000267028809},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.5490000247955322}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6315000057220459},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5468000173568726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310999751091003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49889999628067017},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.490200012922287},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4498000144958496},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.426800012588501},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4106999933719635},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36640000343322754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3467000126838684},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3314000070095062},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2897999882698059},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2768999934196472},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C162984825","wikidata":"https://www.wikidata.org/wiki/Q339072","display_name":"Database normalization","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.04106","doi":"https://doi.org/10.48550/arxiv.2611.04106","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04106","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2611.04106","doi":"https://doi.org/10.48550/arxiv.2611.04106","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04106","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7223403067","https://openalex.org/W3194378189","https://openalex.org/W7221651935","https://openalex.org/W7221135742","https://openalex.org/W4327653014","https://openalex.org/W7164129011","https://openalex.org/W4404600560","https://openalex.org/W3198802556","https://openalex.org/W7133229197","https://openalex.org/W3182384796"],"abstract_inverted_index":{"What":[0],"makes":[1],"a":[2,8,66,70,117,143,147,174,178,194],"pretraining":[3,114,153],"corpus":[4,9,119,150],"transferable?":[5],"We":[6,25],"describe":[7],"by":[10,177],"three":[11],"properties:":[12],"its":[13,15],"structure,":[14,76],"dimensionality,":[16,77],"and":[17,42,78,108,124,146,167],"the":[18,27,30,47,52,82,94,103,109,121,130,140,161,165,171,183,186,189,212],"distribution":[19,79,104],"shape":[20,105,141,175],"of":[21,85,120,173,180],"each":[22,97],"unit's":[23],"values.":[24],"propose":[26],"Transfer-Invariance":[28],"Principle:":[29],"same":[31,122],"property":[32],"can":[33,58],"be":[34],"irrelevant":[35],"to":[36,199,209],"transfer":[37],"under":[38,44],"one":[39],"input":[40,49,98,162],"transform":[41],"decisive":[43],"another,":[45],"so":[46,182],"model's":[48],"transform,":[50],"not":[51,185],"data":[53,168,205,218],"modality,":[54,187],"decides":[55],"which":[56],"properties":[57],"matter.":[59],"To":[60],"test":[61],"it":[62,89,126],"we":[63],"build":[64],"TransferForge,":[65],"generator":[67],"that":[68,196],"places":[69],"synthetic":[71,83,149],"population":[72],"at":[73],"any":[74,202],"prescribed":[75],"shape.":[80],"KernelSynth,":[81],"prior":[84],"Chronos,":[86],"cannot,":[87],"because":[88],"draws":[90],"independent":[91],"series.":[92],"When":[93,129],"model":[95,131,166],"standardizes":[96],"window":[99],"(PatchTST":[100],"on":[101],"UCR),":[102],"is":[106,219],"inert":[107],"structural":[110],"setting":[111],"governs.":[112],"Synthetic":[113],"then":[115,206],"matches":[116],"real":[118,152,156,217],"size":[123],"exceeds":[125],"once":[127],"scaled.":[128],"encodes":[132],"calcium":[133],"fluorescence":[134],"signals":[135],"without":[136],"normalization":[137],"(POYO":[138],"Plus),":[139],"becomes":[142,207],"governing":[144],"constraint,":[145],"shape-matched":[148],"replaces":[151],"with":[154,164],"zero":[155],"neural":[157],"activity.":[158],"Flipping":[159],"only":[160],"normalization,":[163],"fixed,":[169],"changes":[170],"effect":[172],"manipulation":[176],"factor":[179],"5.3,":[181],"pipeline,":[184],"sets":[188],"switch.":[190],"The":[191],"principle":[192],"yields":[193],"recipe":[195],"chooses":[197],"what":[198],"synthesize":[200],"before":[201],"training.":[203],"Pretraining":[204],"something":[208],"manufacture":[210],"for":[211],"model,":[213],"most":[214],"valuably":[215],"where":[216],"scarce,":[220],"expensive,":[221],"or":[222],"private.":[223]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}