{"id":"https://openalex.org/W7225819651","doi":"https://doi.org/10.5281/zenodo.24144829","title":"Viveka: Separating Real Gains from Chance in Self-Improving Agents","display_name":"Viveka: Separating Real Gains from Chance in Self-Improving Agents","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225819651","doi":"https://doi.org/10.5281/zenodo.24144829"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24144829","doi":"https://doi.org/10.5281/zenodo.24144829","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24144829","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.24144829","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160888945","display_name":"Sayan Chowdhury","orcid":"https://orcid.org/0009-0004-8421-0087","observed_orcids":["https://orcid.org/0009-0004-8421-0087"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chowdhury, Sayan","raw_affiliation_strings":["Kalaris Labs"],"raw_orcid":"https://orcid.org/0009-0004-8421-0087","affiliations":[{"raw_affiliation_string":"Kalaris Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160888945"],"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.4016000032424927,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.4016000032424927,"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/T10260","display_name":"Software Engineering Research","score":0.11100000143051147,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.09350000321865082,"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/C136815107","wikidata":"https://www.wikidata.org/wiki/Q154242","display_name":"Nothing","level":2,"score":0.5902000069618225},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46560001373291016},{"id":"https://openalex.org/C2778049214","wikidata":"https://www.wikidata.org/wiki/Q7512234","display_name":"Sigma","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C188721877","wikidata":"https://www.wikidata.org/wiki/Q103510","display_name":"Bar (unit)","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3133000135421753},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.30250000953674316},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C77265313","wikidata":"https://www.wikidata.org/wiki/Q879844","display_name":"Rest (music)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C23119410","wikidata":"https://www.wikidata.org/wiki/Q236908","display_name":"Six Sigma","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2653000056743622},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24144829","doi":"https://doi.org/10.5281/zenodo.24144829","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24144829","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.24144830","doi":"https://doi.org/10.5281/zenodo.24144830","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24144830","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.24144829","doi":"https://doi.org/10.5281/zenodo.24144829","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24144829","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":{"Agents":[0],"that":[1,26,33,56,84,100,134],"improve":[2],"their":[3],"own":[4],"harness":[5],"usually":[6],"keep":[7,31],"a":[8,11,54,74,97,141,152,166,174,187,196],"change":[9,55,75,108],"when":[10,119,157],"score":[12,80],"goes":[13],"up.":[14],"That":[15],"is":[16,59,76,122,161],"weak":[17],"evidence.":[18],"Agent":[19],"evaluations":[20],"are":[21,69],"noisy,":[22],"and":[23,130],"an":[24,205],"agent":[25,113],"tries":[27],"many":[28,67],"changes":[29,133],"will":[30],"some":[32],"only":[34],"looked":[35],"better":[36],"by":[37],"chance.":[38],"We":[39,94,193],"show":[40],"two":[41],"simple":[42,142],"facts.":[43],"Under":[44],"the":[45,62,82,103,112,120,148,158,201],"usual":[46,149],"\"keep":[47],"it":[48,50],"if":[49],"scores":[51,126],"higher\"":[52],"rule,":[53],"does":[57],"nothing":[58],"kept":[60],"half":[61],"time,":[63],"no":[64],"matter":[65],"how":[66],"seeds":[68,111,179],"used.":[70],"And":[71],"once":[72],"such":[73],"kept,":[77],"its":[78],"lucky":[79,125],"becomes":[81],"bar":[83],"real":[85,90,159,167,191],"improvements":[86],"must":[87],"clear,":[88,123],"so":[89],"progress":[91],"slows":[92],"down.":[93],"propose":[95],"Viveka,":[96],"checking":[98],"layer":[99],"sits":[101],"outside":[102],"agent.":[104,209],"It":[105],"re-tests":[106],"each":[107],"on":[109,177,204],"fresh":[110,128],"has":[114],"never":[115],"seen,":[116],"stops":[117],"early":[118],"answer":[121],"replaces":[124],"with":[127,195],"ones,":[129],"later":[131],"removes":[132],"turn":[135],"out":[136],"not":[137,189],"to":[138],"matter.":[139],"In":[140],"simulation":[143],"of":[144,154,169],"100":[145],"proposed":[146],"changes,":[147],"rule":[150],"reports":[151],"gain":[153,160,168],"1.92":[155],"sigma":[156],"0.52":[162],"sigma.":[163,182],"Viveka":[164],"reaches":[165,180],"1.43":[170],"sigma,":[171],"while":[172],"spending":[173],"similar":[175],"budget":[176],"extra":[178],"0.82":[181],"These":[183],"numbers":[184],"come":[185],"from":[186,190],"simulation,":[188],"agents.":[192],"end":[194],"fixed":[197],"plan":[198],"for":[199],"testing":[200],"same":[202],"claims":[203],"open-source":[206],"self-refining":[207],"coding":[208]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}