{"id":"https://openalex.org/W7225146353","doi":"https://doi.org/10.20944/preprints202611.0191.v1","title":"Correctness Before Reuse: A CPU Contract Pilot for Kernel Optimization Memory","display_name":"Correctness Before Reuse: A CPU Contract Pilot for Kernel Optimization Memory","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225146353","doi":"https://doi.org/10.20944/preprints202611.0191.v1"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202611.0191.v1","doi":"https://doi.org/10.20944/preprints202611.0191.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0191.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202611.0191.v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055936582","display_name":"Saurav Keshari Aryal","orcid":"https://orcid.org/0000-0001-9815-9295","observed_orcids":["https://orcid.org/0000-0001-9815-9295"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Saurav K. Aryal","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9815-9295","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5055936582"],"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8192999958992004,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8192999958992004,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.09510000050067902,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10126","display_name":"Logic, programming, and type systems","score":0.04809999838471413,"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/rmsnorm","display_name":"RMSNorm","score":0.6430000066757202},{"id":"https://openalex.org/keywords/softmax-function","display_name":"softmax","score":0.7110000252723694},{"id":"https://openalex.org/keywords/decimal-arithmetic","display_name":"decimal arithmetic","score":0.40400001406669617},{"id":"https://openalex.org/keywords/fault-injection","display_name":"fault injection","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044000267982483},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5455999970436096},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.48339998722076416},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41019999980926514},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C41661131","wikidata":"https://www.wikidata.org/wiki/Q220764","display_name":"Interrupt","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C201932085","wikidata":"https://www.wikidata.org/wiki/Q642514","display_name":"Online analytical processing","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C2776350369","wikidata":"https://www.wikidata.org/wiki/Q843479","display_name":"Control logic","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.2969000041484833},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C56951928","wikidata":"https://www.wikidata.org/wiki/Q3539213","display_name":"Trimming","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C56348326","wikidata":"https://www.wikidata.org/wiki/Q1047554","display_name":"Mutual exclusion","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C2777145635","wikidata":"https://www.wikidata.org/wiki/Q515636","display_name":"FIFO (computing and electronics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C193343404","wikidata":"https://www.wikidata.org/wiki/Q1928607","display_name":"Page fault","level":5,"score":0.2662999927997589},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20944/preprints202611.0191.v1","doi":"https://doi.org/10.20944/preprints202611.0191.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0191.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202611.0191.v1","doi":"https://doi.org/10.20944/preprints202611.0191.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0191.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"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/W7155960929","https://openalex.org/W7172002712","https://openalex.org/W7214040534","https://openalex.org/W7220675661","https://openalex.org/W7167628274","https://openalex.org/W4404346978","https://openalex.org/W7212244474","https://openalex.org/W7204265497","https://openalex.org/W7155569127","https://openalex.org/W3158969310"],"abstract_inverted_index":{"A":[0,35,69,124,169],"kernel":[1,155],"that":[2],"returns":[3],"a":[4,20,26,73,87,115],"plausible":[5],"value":[6],"on":[7,44],"its":[8],"first":[9],"input":[10,112],"may":[11],"fail":[12],"when":[13],"runtime":[14],"values,":[15],"specialization":[16,102],"parameters,":[17],"layout,":[18],"or":[19,157],"partial":[21],"tile":[22],"changes.":[23],"We":[24],"report":[25],"completed":[27],"CPU":[28],"validation":[29,152],"pilot":[30],"for":[31],"such":[32],"reuse":[33],"boundaries.":[34],"frozen":[36,135],"registry":[37],"of":[38,81],"eight":[39],"host":[40,70],"implementations":[41],"is":[42],"evaluated":[43],"192":[45],"cases":[46,63],"across":[47,193],"addition,":[48],"masked":[49],"row":[50],"softmax,":[51],"and":[52,64,72,119,141,191],"RMSNorm,":[53],"producing":[54],"1,536":[55],"candidate-case":[56],"checks.":[57,68],"The":[58,160],"suite":[59],"contains":[60],"128":[61],"nonempty":[62,144],"64":[65],"empty-shape":[66],"contract":[67],"reference":[71],"complete":[74],"dispatch-metadata":[75],"key":[76],"pass":[77,86],"all":[78,130,138],"cases.":[79],"Five":[80],"six":[82],"seeded":[83],"fault":[84,93],"controls":[85],"benign":[88],"first-input":[89],"gate,":[90],"yet":[91],"every":[92],"control":[94],"fails":[95],"at":[96],"least":[97],"one":[98],"stronger":[99],"check.":[100],"Shape-only":[101],"passes":[103],"48/192,":[104],"cached":[105],"outputs":[106],"128/192,":[107],"dropped":[108],"tail":[109],"rows":[110],"102/192,":[111],"mutation":[113],"160/192,":[114],"float16":[116],"shortcut":[117],"133/192,":[118],"naive":[120],"float32":[121],"reduction":[122],"188/192.":[123],"separate":[125],"50-digit":[126],"Decimal":[127],"implementation":[128],"verifies":[129],"target":[131],"arrays":[132],"within":[133],"the":[134,175,182],"tolerance,":[136],"replays":[137],"candidate":[139],"checks,":[140],"confirms":[142],"40":[143],"input/oracle":[145],"identities.":[146],"These":[147],"results":[148],"establish":[149],"an":[150],"auditable":[151],"artifact,":[153],"not":[154],"speedup":[156],"learned":[158],"optimization.":[159],"memory":[161],"stores":[162],"dispatch":[163],"metadata":[164],"rather":[165],"than":[166],"compiled":[167],"code.":[168],"separate,":[170],"uncompiled":[171],"NKI":[172],"entrypoint":[173],"documents":[174],"next":[176],"target-device":[177],"stage.":[178],"Future":[179],"work":[180],"applies":[181],"gate":[183],"to":[184],"actual":[185],"Trainium":[186],"compilation,":[187],"profiling,":[188],"generated":[189],"candidates,":[190],"transfer":[192],"workload":[194],"families":[195],"under":[196],"bounded":[197],"credits.":[198]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}
