{"id":"https://openalex.org/W7225016291","doi":"https://doi.org/10.5281/zenodo.23832150","title":"Information-Theoretic Identifiability of Split-Mark Diagnostic Posets, L1 Micro-Syntax Transfer Independence, and Sentence-Level Propositional Conservation in English Prose (1818-2026)","display_name":"Information-Theoretic Identifiability of Split-Mark Diagnostic Posets, L1 Micro-Syntax Transfer Independence, and Sentence-Level Propositional Conservation in English Prose (1818-2026)","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7225016291","doi":"https://doi.org/10.5281/zenodo.23832150"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23832150","doi":"https://doi.org/10.5281/zenodo.23832150","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23832150","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.23832150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015646098","display_name":"Gareth Montgomery","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Montgomery, Gareth","raw_affiliation_strings":["Sprucefield Research, Lisburn, Northern Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sprucefield Research, Lisburn, Northern Ireland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5015646098"],"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/T10467","display_name":"Psychometric Methodologies and Testing","score":0.305400013923645,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.305400013923645,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.1281999945640564,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10021","display_name":"EFL/ESL Teaching and Learning","score":0.09619999676942825,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/syntactic-frames","display_name":"syntactic frames","score":0.3019999861717224},{"id":"https://openalex.org/keywords/second-language-acquisition","display_name":"second language acquisition","score":0.39100000262260437}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5730999708175659},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45010000467300415},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.42570000886917114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42250001430511475},{"id":"https://openalex.org/C2779835924","wikidata":"https://www.wikidata.org/wiki/Q146786","display_name":"Plural","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3955000042915344},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.3562999963760376},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C180645754","wikidata":"https://www.wikidata.org/wiki/Q474715","display_name":"Partially ordered set","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C2776212696","wikidata":"https://www.wikidata.org/wiki/Q576271","display_name":"Determiner","level":3,"score":0.34619998931884766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3456999957561493},{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C162392398","wikidata":"https://www.wikidata.org/wiki/Q272404","display_name":"Finite set","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2778523021","wikidata":"https://www.wikidata.org/wiki/Q5532504","display_name":"Quantifier (linguistics)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23832150","doi":"https://doi.org/10.5281/zenodo.23832150","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23832150","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.23832151","doi":"https://doi.org/10.5281/zenodo.23832151","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23832151","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.23832150","doi":"https://doi.org/10.5281/zenodo.23832150","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23832150","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3121258224","https://openalex.org/W6921471861","https://openalex.org/W3187028098","https://openalex.org/W7034221660","https://openalex.org/W1543626814","https://openalex.org/W2243401215","https://openalex.org/W1544198189","https://openalex.org/W6989925215","https://openalex.org/W2750133449","https://openalex.org/W2403874552"],"abstract_inverted_index":{"This":[0],"monograph":[1],"establishes":[2],"four":[3],"interconnected":[4],"results":[5],"across":[6,38,143,276],"cognitive":[7],"diagnostic":[8],"psychometrics,":[9],"second-language":[10],"acquisition":[11],"(SLA)":[12],"corpus":[13,249,289],"linguistics,":[14],"and":[15,115,136,152,217,288,295],"quantitative":[16],"diachronic":[17,248],"philology:":[18],"Split-Mark":[19,89],"Poset":[20],"Identifiability:":[21],"In":[22],"Cambridge":[23,130],"C1/C2":[24,139,225],"Key":[25],"Word":[26],"Transformation":[27],"(Part":[28],"4)":[29],"testing,":[30],"each":[31],"item":[32],"awards":[33],"up":[34],"to":[35,198,280],"2":[36],"marks":[37],"two":[39,277],"syntactic":[40,69],"loci,":[41],"yet":[42],"standard":[43],"reporting":[44],"collapses":[45],"the":[46,55],"ordered":[47,88],"binary":[48],"vector":[49,90],"(m_L,":[50],"m_R)":[51],"in":[52,63,96,186,190],"{0,1}^2":[53],"into":[54],"scalar":[56,113],"sum":[57],"S":[58],"=":[59,73,82,98,110,117,128,202,205,234,238,260,268,283],"m_L":[60],"+":[61],"m_R":[62],"{0,1,2}.":[64],"Over":[65],"a":[66,172,245],"5-attribute":[67],"hierarchical":[68],"poset":[70,94],"with":[71,108,231],"|S|":[72],"10":[74],"permissible":[75],"mastery":[76],"states":[77],"(prior":[78],"Shannon":[79,214],"entropy":[80],"log_2(10)":[81],"3.3219":[83],"bits),":[84],"we":[85],"prove":[86],"that":[87,159],"scoring":[91],"achieves":[92],"full":[93],"identifiability":[95],"N_min(V)":[97],"3":[99],"static":[100],"items":[101,105,135],"(and":[102],"2.3000":[103],"expected":[104],"adaptively),":[106],"compared":[107],"N_min(S)":[109],"4":[111,134],"for":[112,119],"sums":[114],"N_min(D)":[116],"5":[118],"dichotomous":[120],"scoring.":[121],"The":[122],"Macro/Micro":[123],"Decoupling":[124],"Paradox:":[125],"Auditing":[126],"N":[127],"80":[129],"C2":[131],"Proficiency":[132],"Part":[133],"14":[137],"longitudinal":[138],"scripts":[140],"(3,886":[141],"words":[142],"322":[144],"sentences)":[145],"from":[146,227],"zero-article":[147],"Slavic/Baltic":[148,187],"(Russian,":[149],"Ukrainian,":[150],"Lithuanian)":[151],"Romance":[153],"(Italian,":[154],"French)":[155],"L1":[156,180,199],"learners":[157],"reveals":[158],"candidates":[160],"attain":[161],"96.9%":[162],"accuracy":[163],"on":[164],"C1":[165],"macro-syntactic":[166],"frames":[167],"while":[168,192,252],"remaining":[169],"capped":[170],"at":[171,293],"21.4%":[173],"Error-Free":[174],"Sentence":[175],"Ratio":[176],"(EFSR)":[177],"by":[178,257,265],"deterministic":[179],"micro-syntax":[181],"transfer":[182],"(50.8%":[183],"determiner":[184],"errors":[185],"vs":[188],"26.8%":[189],"Romance),":[191],"macro-frame":[193],"deployment":[194],"is":[195],"statistically":[196],"invariant":[197,275],"family":[200],"(chi^2":[201],"0.3113,":[203],"p":[204,237,282],"0.7258).":[206],"Closed-Class":[207],"Syntactic":[208],"Cadence":[209],"Entropy:":[210],"Combining":[211],"Clause-Initial":[212],"Opener":[213],"Entropy":[215,221],"(H_opener)":[216],"Punctuation":[218],"Markov":[219],"Transition":[220],"(H_punct)":[222],"separates":[223],"authentic":[224],"prose":[226,230],"formulaic":[228],"template":[229],"ROC":[232],"AUC":[233],"1.000":[235],"(Mann-Whitney":[236],"1.08e-5).":[239],"Sentence-Level":[240],"Propositional":[241],"Conservation":[242],"(1800-2026):":[243],"Across":[244],"balanced":[246],"36-text":[247],"(5,296":[250],"words),":[251],"finite":[253],"subordination":[254],"density":[255],"decayed":[256],"52.6%":[258],"(p":[259,267],"1.98e-5),":[261],"nominal-participial":[262],"compression":[263],"surged":[264],"240.0%":[266],"1.43e-8),":[269],"holding":[270],"total":[271],"propositions":[272],"per":[273],"sentence":[274],"centuries":[278],"(2.70":[279],"2.92,":[281],"0.4778).":[284],"Interactive":[285],"browser":[286],"verifiers":[287],"diagnostics":[290],"are":[291],"hosted":[292],"https://garethenglish.com/sprucefield-research.html":[294],"https://garethenglish.com/c1-syntactic-research-lab.html.":[296]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-11-01T00:00:00"}