{"id":"https://openalex.org/W4417517251","doi":"https://doi.org/10.48550/arxiv.2505.07728","title":"Guiding Data Collection via Factored Scaling Curves","display_name":"Guiding Data Collection via Factored Scaling Curves","publication_year":2025,"publication_date":"2025-05-12","ids":{"openalex":"https://openalex.org/W4417517251","doi":"https://doi.org/10.48550/arxiv.2505.07728"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.07728","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07728","pdf_url":"https://arxiv.org/pdf/2505.07728","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.07728","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039381213","display_name":"Lihan Zha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zha, Lihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091468806","display_name":"Apurva Badithela","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Badithela, Apurva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612835","display_name":"Michael Zhang","orcid":"https://orcid.org/0000-0002-7067-0689"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060177564","display_name":"Justin Lidard","orcid":"https://orcid.org/0000-0001-8316-1018"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lidard, Justin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bao, Jeremy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Jeremy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077369857","display_name":"Emily Zhou","orcid":"https://orcid.org/0009-0009-5004-6588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Emily","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020423812","display_name":"D. B. Snyder","orcid":"https://orcid.org/0000-0003-3462-5650"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Snyder, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020154600","display_name":"Allen Z. Ren","orcid":"https://orcid.org/0000-0001-5306-2844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Allen Z.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061979493","display_name":"Dhruv Shah","orcid":"https://orcid.org/0000-0002-7541-3278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shah, Dhruv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013839863","display_name":"Anirudha Majumdar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Majumdar, Anirudha","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":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/T10653","display_name":"Robot Manipulation and Learning","score":0.8873000144958496,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8873000144958496,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.03319999948143959,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.010599999688565731,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.694100022315979},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.6599000096321106},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5695000290870667},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5580000281333923},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5267000198364258},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5163999795913696},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5041999816894531},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.4650000035762787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6970000267028809},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.694100022315979},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.6599000096321106},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4943999946117401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4674000144004822},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45739999413490295},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.07728","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07728","pdf_url":"https://arxiv.org/pdf/2505.07728","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.07728","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.07728","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,"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":"pmh:oai:arXiv.org:2505.07728","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.07728","pdf_url":"https://arxiv.org/pdf/2505.07728","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2042506886","display_name":null,"funder_award_id":"N00014-23-1-2148","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2738933117","display_name":"CAREER: Generalization and Safety Guarantees for Learning-Based Control of Robots","funder_award_id":"2044149","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417517251.pdf","grobid_xml":"https://content.openalex.org/works/W4417517251.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generalist":[0],"imitation":[1],"learning":[2],"policies":[3,23],"trained":[4,27],"on":[5],"large":[6,33],"datasets":[7],"show":[8,126],"great":[9],"promise":[10],"for":[11,58,69,98],"solving":[12],"diverse":[13],"manipulation":[14],"tasks.":[15],"However,":[16],"to":[17,20,25,62,67,140],"ensure":[18],"generalization":[19],"different":[21],"conditions,":[22],"need":[24],"be":[26],"with":[28],"data":[29,61,85,96,156],"collected":[30],"across":[31,119],"a":[32,46,55,105],"set":[34],"of":[35],"environmental":[36],"factor":[37,71,102],"variations":[38],"(e.g.,":[39],"camera":[40],"pose,":[41],"table":[42],"height,":[43],"distractors)":[44],"$-$":[45],"prohibitively":[47],"expensive":[48],"undertaking,":[49],"if":[50],"done":[51],"exhaustively.":[52],"We":[53,108,146],"introduce":[54],"principled":[56],"method":[57,112],"deciding":[59],"what":[60],"collect":[63,68],"and":[64,116,122,125],"how":[65,80,149],"much":[66],"each":[70],"by":[72,138],"constructing":[73],"factored":[74,150],"scaling":[75,151],"curves":[76,93,152],"(FSC),":[77],"which":[78],"quantify":[79],"policy":[81],"performance":[82],"varies":[83],"as":[84],"scales":[86],"along":[87],"individual":[88],"or":[89],"paired":[90],"factors.":[91],"These":[92],"enable":[94],"targeted":[95],"acquisition":[97],"the":[99,110],"most":[100],"influential":[101],"combinations":[103],"within":[104],"given":[106],"budget.":[107],"evaluate":[109],"proposed":[111],"through":[113],"extensive":[114],"simulated":[115],"real-world":[117,133,164],"experiments,":[118],"both":[120],"training-from-scratch":[121],"fine-tuning":[123],"settings,":[124],"that":[127],"it":[128],"boosts":[129],"success":[130],"rates":[131],"in":[132,135],"tasks":[134],"new":[136],"environments":[137],"up":[139],"26%":[141],"over":[142],"existing":[143],"data-collection":[144],"strategies.":[145],"further":[147],"demonstrate":[148],"can":[153],"effectively":[154],"guide":[155],"collection":[157],"using":[158],"an":[159],"offline":[160],"metric,":[161],"without":[162],"requiring":[163],"evaluation":[165],"at":[166],"scale.":[167]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}