The Missing Variable in AI-Assisted Litigation: Architecture and the Quality of Pro Se Access to Justice

{"Version":[0],"of":[1,41,86,103,109,122,143,186,216,222,238,253,272],"record:":[2],"SSRN":[3],"7120940,":[4],"DOI":[5],"10.2139/ssrn.7120940.":[6],"Cite":[7],"that":[8,27,50,58,226],"version.":[9],"The":[10,56,114,214,230,274,297],"same":[11,267],"text":[12,30],"is":[13,21,53,61,99,118,219,246,299,312],"also":[14],"at":[15],"https://vadymchernets.netlify.app/missing-variable.html":[16],"and":[17,64,126,188,264,292,306,318],"https://github.com/vadimchernets/papers/tree/main/missing-variable.":[18],"This":[19],"deposit":[20],"an":[22,47,80,247,261],"archival":[23],"copy":[24],"made":[25],"so":[26],"the":[28,93,107,119,131,148,220,223,228,233,236,251,266,270,282,294,310,313,315,319],"full":[29],"stays":[31],"retrievable;":[32],"it":[33,127],"makes":[34],"no":[35,141],"separate":[36],"claim.":[37],"Nearly":[38],"every":[39],"account":[40,133],"AI":[42,51,104,239],"in":[43,158,194,207,250,256,289],"litigation":[44,255],"rests":[45],"on":[46],"unstated":[48],"assumption:":[49],"assistance":[52,105],"one":[54,123],"thing.":[55],"debate":[57],"assumption":[59],"produces":[60],"about":[62],"volume":[63],"fabrication:":[65],"a":[66,83,129,151,180,190,195,208,302,307],"federal":[67,124,286],"pro":[68],"se":[69],"plaintiff":[70],"rate":[71],"up":[72,278],"from":[73,204],"11%":[74],"to":[75],"nearly":[76],"17%,":[77],"courts":[78,287],"describing":[79],"\\"existential":[81],"threat,\\"":[82],"growing":[84],"docket":[85,121],"sanctions":[87],"decisions":[88],"over":[89],"fabricated":[90],"citations.":[91],"What":[92],"aggregate":[94],"studies":[95],"cannot":[96],"yet":[97],"show":[98],"whether":[100],"any":[101,144],"configuration":[102],"changes":[106],"quality":[108,252],"what":[110],"self-represented":[111,138,254],"litigants":[112],"do.":[113],"record":[115],"used":[116],"here":[117,279],"public":[120],"case,":[125],"holds":[128],"pattern":[130],"volume-and-hallucination":[132],"does":[134],"not":[135,260,265],"predict.":[136],"A":[137],"litigant":[139],"with":[140],"attorney":[142],"kind,":[145],"using,":[146],"by":[147,202],"author's":[149],"account,":[150],"multi-model":[152,244],"orchestration":[153],"system":[154,316],"(independent":[155],"models":[156],"queried":[157],"parallel,":[159],"disagreement":[160],"surfaced":[161],"rather":[162],"than":[163],"averaged":[164],"away,":[165],"citations":[166],"verified":[167],"against":[168],"external":[169],"sources),":[170],"answered":[171],"six":[172,183],"coordinated":[173],"pre-motion":[174],"letters":[175],"within":[176],"four":[177],"days,":[178],"filed":[179,197],"substantive":[181],"opposition":[182],"weeks":[184],"ahead":[185],"deadline,":[187],"identified":[189],"verifiable":[191],"statutory-citation":[192],"error":[193],"brief":[196],"for":[198,281,293],"seven":[199],"defendants":[200],"represented":[201],"counsel":[203],"leading":[205],"firms,":[206],"case":[209,298],"naming":[210],"thirteen":[211],"technology":[212],"defendants.":[213],"last":[215],"those":[217],"three":[218],"inverse":[221],"failure":[224],"mode":[225],"dominates":[227],"literature.":[229],"Article":[231],"proposes":[232],"architecture-dependence":[234],"hypothesis:":[235],"architecture":[237],"assistance,":[240],"single-model":[241],"prompting":[242],"versus":[243],"orchestration,":[245],"empirical":[248],"variable":[249],"its":[257],"own":[258],"right,":[259],"implementation":[262],"detail":[263],"thing":[268],"as":[269,301],"availability":[271],"AI.":[273],"doctrinal":[275],"consequences":[276],"taken":[277],"are":[280],"work-product":[283],"doctrine,":[284],"where":[285],"split":[288],"early":[290],"2026,":[291],"unauthorized-practice":[295],"framework.":[296],"offered":[300],"falsifiable":[303],"existence":[304],"proof":[305],"research":[308],"agenda;":[309],"author":[311],"plaintiff,":[314],"developer,":[317],"analyst.":[320]}

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-09-19
DOI
https://doi.org/10.5281/zenodo.22168724
Primary Topic
Artificial Intelligence in Law
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
preprint

The Missing Variable in AI-Assisted Litigation: Architecture and the Quality of Pro Se Access to Justice

Vadym Chernets
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Law
preprint

The Missing Variable in AI-Assisted Litigation: Architecture and the Quality of Pro Se Access to Justice

Vadym Chernets
preprint en

Abstract

Version of record: SSRN 7120940, DOI 10.2139/ssrn.7120940. Cite that version. The same text is also at https://vadymchernets.netlify.app/missing-variable.html and https://github.com/vadimchernets/papers/tree/main/missing-variable. This deposit is an archival copy made so that the full text stays retrievable; it makes no separate claim. Nearly every account of AI in litigation rests on an unstated assumption: that AI assistance is one thing. The debate that assumption produces is about volume and fabrication: a federal pro se plaintiff rate up from 11% to nearly 17%, courts describing an "existential threat," a growing docket of sanctions decisions over fabricated citations. What the aggregate studies cannot yet show is whether any configuration of AI assistance changes the quality of what self-represented litigants do. The record used here is the public docket of one federal case, and it holds a pattern the volume-and-hallucination account does not predict. A self-represented litigant with no attorney of any kind, using, by the author's account, a multi-model orchestration system (independent models queried in parallel, disagreement surfaced rather than averaged away, citations verified against external sources), answered six coordinated pre-motion letters within four days, filed a substantive opposition six weeks ahead of deadline, and identified a verifiable statutory-citation error in a brief filed for seven defendants represented by counsel from leading firms, in a case naming thirteen technology defendants. The last of those three is the inverse of the failure mode that dominates the literature. The Article proposes the architecture-dependence hypothesis: the architecture of AI assistance, single-model prompting versus multi-model orchestration, is an empirical variable in the quality of self-represented litigation in its own right, not an implementation detail and not the same thing as the availability of AI. The doctrinal consequences taken up here are for the work-product doctrine, where federal courts split in early 2026, and for the unauthorized-practice framework. The case is offered as a falsifiable existence proof and a research agenda; the author is the plaintiff, the system developer, and the analyst.

Zenodo (CERN European Organization for Nuclear Research)
Peace, Justice and strong institutions
Artificial Intelligence in Law
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.