{"id":"https://openalex.org/W7224305752","doi":"https://doi.org/10.5281/zenodo.23778626","title":"The judge cannot see the margin: a paired ablation of a mechanical proof step in a model-run design pipeline","display_name":"The judge cannot see the margin: a paired ablation of a mechanical proof step in a model-run design pipeline","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224305752","doi":"https://doi.org/10.5281/zenodo.23778626"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23778626","doi":"https://doi.org/10.5281/zenodo.23778626","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23778626","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","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23778626","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109975182","display_name":"Aditya Reddy","orcid":"https://orcid.org/0009-0009-3175-7341","observed_orcids":["https://orcid.org/0009-0009-3175-7341"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Reddy, Aditya","raw_affiliation_strings":["Independent researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5109975182"],"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":0.2992999851703644,"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":0.2992999851703644,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.06729999929666519,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14254","display_name":"Digital Media and Visual Art","score":0.035599999129772186,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/claude-opus","display_name":"Claude Opus","score":0.5820000171661377},{"id":"https://openalex.org/keywords/design-quality-control","display_name":"design quality control","score":0.3050000071525574},{"id":"https://openalex.org/keywords/human-ai-collaboration","display_name":"human-AI collaboration","score":0.49900001287460327}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.6104999780654907},{"id":"https://openalex.org/C124978682","wikidata":"https://www.wikidata.org/wiki/Q1201019","display_name":"Proof of concept","level":2,"score":0.6103000044822693},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6039000153541565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5583999752998352},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C2776545233","wikidata":"https://www.wikidata.org/wiki/Q1064858","display_name":"Desk","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C2777063073","wikidata":"https://www.wikidata.org/wiki/Q1553237","display_name":"Settlement (finance)","level":3,"score":0.3743000030517578},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C195653647","wikidata":"https://www.wikidata.org/wiki/Q7625047","display_name":"Structural proof theory","level":4,"score":0.3458000123500824},{"id":"https://openalex.org/C13766981","wikidata":"https://www.wikidata.org/wiki/Q11387554","display_name":"Automated proof checking","level":3,"score":0.33869999647140503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25859999656677246},{"id":"https://openalex.org/C162372511","wikidata":"https://www.wikidata.org/wiki/Q218341","display_name":"Checksum","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C2318724","wikidata":"https://www.wikidata.org/wiki/Q852732","display_name":"Proof theory","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23778626","doi":"https://doi.org/10.5281/zenodo.23778626","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23778626","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.23778627","doi":"https://doi.org/10.5281/zenodo.23778627","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23778627","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.23778626","doi":"https://doi.org/10.5281/zenodo.23778626","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23778626","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":["https://openalex.org/W7214146906","https://openalex.org/W7201981943","https://openalex.org/W49084991","https://openalex.org/W7203939229","https://openalex.org/W6989173082","https://openalex.org/W4214575876","https://openalex.org/W7202253095","https://openalex.org/W7214483336","https://openalex.org/W3209520223","https://openalex.org/W2338081809"],"abstract_inverted_index":{"Desk":[0],"Studio":[1],"runs":[2],"a":[3,7,12,15,17,21,29,36,54,63,72,128,146,168,173,178,211,236,241,260],"design":[4],"job":[5,114,147],"as":[6,100],"loop":[8],"of":[9,134,204,216,231],"model":[10,66,95],"calls:":[11],"builder":[13,174],"polishes":[14],"card,":[16],"browser":[18],"renders":[19],"it,":[20],"proof":[22,117,139,170,191,208],"step":[23,50],"measures":[24],"the":[25,33,43,48,77,118,152,205,226,232,263,271],"rendered":[26,264],"pixels,":[27],"and":[28,38,79,85,92,98,124,159,176,192,223,270],"Creative":[30],"Director":[31],"scores":[32,200],"screenshots":[34],"against":[35,143,161,219],"rubric":[37,184],"signs":[39],"off":[40,121],"or":[41],"sends":[42],"round":[44,171,239,245],"back.":[45],"Proof":[46],"is":[47,67,254],"one":[49],"that":[51,75,255],"never":[52],"calls":[53],"model.":[55],"I":[56,70,250],"asked":[57],"whether":[58],"it":[59,209,276],"changes":[60],"anything":[61,256],"when":[62],"strong":[64],"vision":[65],"already":[68],"looking.":[69],"added":[71],"flag,":[73],"--no-proof,":[74],"skips":[76],"checks":[78],"leaves":[80],"everything":[81],"else":[82],"in":[83,89,93,104,151,214,259],"place,":[84],"ran":[86],"15":[87],"cases":[88],"both":[90],"arms":[91],"two":[94],"families":[96],"(claude-opus-5-5":[97],"gpt-6-astra":[99],"directors),":[101],"60":[102],"jobs":[103,235],"30":[105,233],"pairs,":[106],"with":[107,190,221],"four":[108],"hypotheses":[109],"written":[110],"down":[111],"before":[112],"any":[113],"finished.":[115],"Without":[116,207],"director":[119,179],"signed":[120,225],"17":[122,126],"files":[123],"all":[125],"failed":[127,169],"hidden":[129],"audit.":[130],"With":[131],"proof,":[132,222],"0":[133],"17.":[135],"Against":[136],"my":[137],"prediction,":[138],"cost":[140],"less,":[141],"0.735":[142],"0.985":[144],"USD":[145],"at":[148],"list":[149],"price":[150],"Anthropic":[153],"family":[154],"(exact":[155],"p":[156],"=":[157,165,196],"0.064)":[158],"1.074":[160],"1.311":[162],"pooled":[163],"(p":[164,195],"0.021),":[166],"because":[167],"costs":[172],"call":[175],"not":[177,187],"call.":[180],"The":[181,248],"director's":[182],"final":[183],"averages":[185],"did":[186],"differ,":[188],"8.49":[189],"8.43":[193],"without":[194],"0.307),":[197],"so":[198],"its":[199,217],"carry":[201],"no":[202],"trace":[203],"faults.":[206],"named":[210],"mechanical":[212],"fault":[213],"13%":[215],"notes,":[218],"1%":[220],"still":[224],"faulty":[227],"files.":[228],"In":[229],"19":[230],"proof-on":[234],"later":[237],"polish":[238],"broke":[240],"check":[242,261],"an":[243],"earlier":[244],"had":[246],"passed.":[247],"rule":[249],"take":[251],"from":[252],"this":[253],"measurable":[257],"belongs":[258],"on":[262],"file,":[265],"run":[266],"after":[267],"every":[268],"round,":[269],"judge":[272],"keeps":[273],"what":[274],"only":[275],"can":[277],"see.":[278]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-10-30T00:00:00"}