{"id":"https://openalex.org/W7225817478","doi":"https://doi.org/10.5281/zenodo.24144799","title":"The Harness Is the Lab: Measured Self-Improvement for Ontology-Grounded AI Scientists","display_name":"The Harness Is the Lab: Measured Self-Improvement for Ontology-Grounded AI Scientists","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225817478","doi":"https://doi.org/10.5281/zenodo.24144799"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24144799","doi":"https://doi.org/10.5281/zenodo.24144799","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24144799","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.24144799","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/T13904","display_name":"Artificial Intelligence Applications","score":0.41990000009536743,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.41990000009536743,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.16429999470710754,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.09109999984502792,"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/C116222747","wikidata":"https://www.wikidata.org/wiki/Q220888","display_name":"Falsifiability","level":2,"score":0.6881999969482422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6389999985694885},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5209000110626221},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C184992742","wikidata":"https://www.wikidata.org/wiki/Q7243229","display_name":"Prime (order theory)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2809999883174896},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2651999890804291},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24144799","doi":"https://doi.org/10.5281/zenodo.24144799","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24144799","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.24144800","doi":"https://doi.org/10.5281/zenodo.24144800","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24144800","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.24144799","doi":"https://doi.org/10.5281/zenodo.24144799","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24144799","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":{"Every":[0],"serious":[1],"AI-scientist":[2],"system":[3,199],"released":[4],"in":[5,152],"2026":[6],"has":[7,200],"converged":[8],"on":[9,180],"the":[10,21,185],"same":[11],"lesson:":[12],"generating":[13],"hypotheses,":[14,156],"code":[15],"and":[16,42,64,82,92,127,158,164],"papers":[17],"is":[18,89,139],"no":[19,197,205],"longer":[20],"hard":[22],"part;":[23],"deciding":[24],"which":[25],"results":[26,207],"deserve":[27],"to":[28],"be":[29,118],"believed":[30],"is.":[31],"Karpathy's":[32],"autoresearch":[33],"showed":[34],"that":[35,101,114,128,148],"a":[36,39,43,48,69,76,79,83,90,93,119,124,135,194],"sealed":[37],"evaluator,":[38],"fixed":[40],"budget":[41],"git":[44],"ratchet":[45],"can":[46],"run":[47],"hundred":[49],"useful":[50],"experiments":[51],"overnight.":[52],"Sakana's":[53],"Agentic":[54],"Scientist,":[55],"Aster,":[56],"Recursive's":[57],"Eureka":[58],"Machine,":[59],"Prime":[60,62],"Intellect's":[61],"Agent":[63],"Edison's":[65],"Kosmos":[66],"each":[67,177],"add":[68],"missing":[70],"piece:":[71],"evidence":[72],"generation,":[73],"massive":[74],"parallelism,":[75],"model-harness":[77],"flywheel,":[78],"self-editing":[80],"harness,":[81],"structured":[84],"world":[85],"model.":[86],"This":[87],"paper":[88],"position":[91],"blueprint.":[94],"We":[95,141,183,203],"argue":[96],"seven":[97],"positions,":[98],"among":[99],"them":[100],"generic":[102],"coding":[103],"harnesses":[104],"are":[105,112],"now":[106],"commodities":[107],"while":[108],"task-evolved":[109],"research":[110,115,146],"scaffolds":[111],"not;":[113],"memory":[116],"must":[117],"typed":[120],"ontology":[121,154],"rather":[122],"than":[123],"chat":[125],"log;":[126],"any":[129],"claim":[130,151],"of":[131,155],"recursive":[132],"self-improvement":[133,195],"without":[134],"held-out":[136,181],"improvement":[137],"curve":[138,196],"marketing.":[140],"then":[142],"describe":[143],"an":[144,153],"open":[145],"harness":[147,173],"grounds":[149],"every":[150],"runs":[157],"results,":[159],"keeps":[160],"its":[161],"evaluators":[162],"sealed,":[163],"improves":[165],"itself":[166],"at":[167],"three":[168],"nested":[169],"levels":[170],"(search":[171],"policy,":[172],"skills,":[174],"model":[175],"weights),":[176],"accepted":[178],"only":[179],"evidence.":[182],"define":[184],"evaluation":[186],"protocol":[187],"we":[188,209],"will":[189],"hold":[190],"ourselves":[191],"to,":[192],"including":[193],"public":[198],"yet":[201],"reported.":[202],"report":[204],"experimental":[206],"here;":[208],"state":[210],"falsifiable":[211],"predictions":[212],"instead.":[213]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}
