{ "vercy": "1.0-draft", "publication": { "status": "research-draft", "adjudicationStatus": "unreviewed", "publishableCanonical": false, "generatedAt": "2026-09-12T11:23:45Z", "providers": [ "Codex" ], "breadth": "recalled by Codex without web access - no source was read", "missingProviders": [], "pass": 2, "cost": { "grok": { "seconds": 19.6, "error": "Reading additional input from stdin...\nOpenAI Codex v0.153.4\n--------\nworkdir: R:\\02_PROJECTS\\02_Meta_Models_Platforms\\Ver.cy\\current\\thing-registry-backlog\nmodel: gpt-6-astra\nprovider: openai\napproval: never\nsandbox: read-only\nreasoning effort: none\nreasoning summaries: none\nsession id: 01a0955a-c5db-7f82-ad06-6bce87b1f24e\n--------\nuser\nDescribe what is already known about one registered thing. Answer as JSON only, no prose around it.\n\nThing: Montenegrin alphabet\nSense to describe: (none recorded)\nDomain code: INF.MED\nAlso known as: (none)\n\n\nContext for this batch of 1001 things:\n# Batch 044:", "usd": 0.0, "recall": true }, "codex": { "seconds": 76.7, "error": "Reading additional input from stdin...\nOpenAI Codex v0.153.4\n--------\nworkdir: R:\\02_PROJECTS\\02_Meta_Models_Platforms\\Ver.cy\\current\\thing-registry-backlog\nmodel: gpt-6-astra\nprovider: openai\napproval: never\nsandbox: read-only\nreasoning effort: none\nreasoning summaries: none\nsession id: 01a0955a-c5cd-71b1-a02c-a80e1a7edf30\n--------\nuser\nYou are drafting a Vercy meta-model for one registered thing. Answer as JSON only, no prose around it.\n\nThing: Montenegrin alphabet\nRegistry id: vr.tr.montenegrin-alphabet\nPlane / domain: INF / INF.MED\nRegistry definition: (none recorded)\nNames folded into thi" } }, "enrichment": { "pass": 3, "engine": "claude", "producedAt": "2026-10-06T12:00:00Z", "ingestedAt": "2026-10-06T08:45:55+00:00", "fields": [ "agent_conduct", "ethics", "failure_modes_and_hazards", "owners", "visual_identification" ] }, "gate": { "passed": true, "version": "1.0", "at": "2026-10-07T10:10:30+00:00", "evidence": [ "completeness 1.00", "sense: Wikidata description", "2 live sources", "review by codex: pass" ] } }, "metaModel": { "id": "THING-Q3403931", "registryId": "vr.tr.montenegrin-alphabet", "name": "Montenegrin alphabet", "version": "0.1.0-research.1", "entryKind": "thing", "family": "Thing Registry", "domain": [ "INF.MED" ], "status": "research-draft" }, "canonicalUrl": "https://ver.cy/models/thing/q3403931/", "model": { "registry_id": "vr.tr.montenegrin-alphabet", "name": "Montenegrin alphabet", "purpose": "Enable an agent to recognise the Montenegrin alphabet, distinguish its script forms and standard versions, and assess whether text operations preserve its letters and distinctions.", "definition": "The Montenegrin alphabet is the set of letters used to write standard Montenegrin, with corresponding Latin and Cyrillic forms, each conventionally comprising 32 letters.", "scope_statement": "This model owns the alphabetic system registered as vr.tr.montenegrin-alphabet in INF / INF.MED, including Latin and Cyrillic inventories, letter identity, ordering, correspondence and digital representation, with claims qualified by the applicable orthographic source.", "in_scope": [ "Latin and Cyrillic forms within one registered alphabet model", "Letter inventories, names, case pairs and alphabetic order", "Distinctive letters Ś and Ź and their Cyrillic correspondents", "Alphabetic treatment of Latin digraphs and corresponding Cyrillic letters", "Version-specific script conversion, encoding and validation requirements" ], "out_of_scope": [ "The Montenegrin language's complete grammar, vocabulary and dialect system", "Complete spelling and punctuation rules beyond their effects on letter interpretation", "Serbian, Croatian and Bosnian alphabets as independently modelled systems", "Individual books, inscriptions, documents and their publication rights", "Fonts, keyboards and text-processing applications as products", "National identity or a writer's language identity inferred solely from script choice" ], "distinguishing_features": [ "Check the declared Montenegrin repertoire and its treatment of Ś and Ź; shared South Slavic letters alone cannot identify the alphabet used by a text.", "Check correspondence between Latin ś/ź and Cyrillic с́/з́; ICANN documents the Cyrillic forms as base letters followed by a combining acute accent. [ICANN Montenegrin Cyrillic reference rules](https://www.icann.org/sites/default/files/packages/lgr/lgr-second-level-montenegrin-cyrillic-language-24jan24-en.html)", "Check whether Latin Dž, Lj and Nj are treated as alphabetic units where appropriate, rather than equating letters with individual encoded characters.", "Distinguish the alphabet's letter repertoire from an orthography's rules for choosing spellings and from the script actually observed in a particular document.", "Treat Latin and Cyrillic as script forms covered by this entry, rather than splitting them into separately registered things." ], "characteristics": [ { "name": "Script form", "kind": "category", "unit_or_values": "Latin; Cyrillic; paired inventory", "why_it_matters": "Determines the applicable letter forms, order and conversion direction." }, { "name": "Orthographic authority and edition", "kind": "relation", "unit_or_values": "Identified orthographic publication, issuing body, edition and relevant pages", "why_it_matters": "Prevents an agent from merging historical proposals and adopted inventories." }, { "name": "Alphabetic inventory size", "kind": "measurement", "unit_or_values": "Number of alphabetic units per script and cited edition", "why_it_matters": "Counts letters independently of digraph length or Unicode code-point count." }, { "name": "Distinctive-letter coverage", "kind": "state", "unit_or_values": "Ś/Ź and с́/з́ covered; partially covered; omitted; unverified", "why_it_matters": "Exposes inventories and implementations that lose Montenegrin-specific distinctions." }, { "name": "Digraph interpretation", "kind": "category", "unit_or_values": "Single alphabetic unit; adjacent independent letters; unresolved in context", "why_it_matters": "Controls segmentation, sorting and script conversion of Dž, Lj and Nj sequences." }, { "name": "Letter correspondence", "kind": "relation", "unit_or_values": "Source letter, target letter or sequence, direction and contextual conditions", "why_it_matters": "Makes conversion rules explicit and distinguishes them from spelling changes." }, { "name": "Representation fidelity", "kind": "state", "unit_or_values": "Distinctions preserved; canonically equivalent representation; lossy substitution; unresolved", "why_it_matters": "Lets an agent judge whether storage, display or conversion has altered letter identity." }, { "name": "Alphabetic position", "kind": "relation", "unit_or_values": "Letter-to-position mapping within a sourced script inventory", "why_it_matters": "Supports alphabetic comparison without assuming Unicode order is linguistic order." } ], "affordances": [ "Compare a proposed inventory with a cited Montenegrin orthographic edition.", "Validate text against a selected repertoire while separately flagging quotations, foreign names and mixed scripts.", "Convert between Latin and Cyrillic with explicit handling of ambiguous digraph sequences.", "Count and sort alphabetic units using script-specific segmentation and ordering rules.", "Detect missing acute accents, script substitutions and other potentially lossy transformations.", "Assess whether a keyboard, font or processing pipeline preserves the required letter distinctions." ], "agent_conduct": { "may": [ "Describe the letters of the Montenegrin alphabet in its Latin and Cyrillic forms from official sources.", "Transliterate text between the two scripts accurately." ], "must_not": [ "Use the alphabet to deny or mock the language identities of people in the region.", "Present one side of language-status disputes as settled.", "Mistranscribe the additional letters that distinguish it." ], "requires_human": [ "Choosing scripts for official or public documents." ] }, "ethics": { "considerations": [ "Language and script are tied to identity and politics in the region.", "Respect for speakers' choices matters." ], "affected_parties": [ "Speakers of Montenegrin", "Neighbouring language communities" ] }, "owners": { "steward": "The public: held in common by its speakers; the state sets the official standard.", "master_systems": [] }, "visual_identification": [ "Written in Latin or Cyrillic script, with letters for the sounds written Ś and Ź in Latin.", "Otherwise looks similar to related South Slavic alphabets." ], "failure_modes_and_hazards": [ "Missing letters in fonts or systems garble names.", "Transliteration errors in official documents." ], "what_it_is_for": [ "The Montenegrin alphabet is used in education, public administration, publishing and everyday communication in standard Montenegrin.", "Its Latin and Cyrillic forms support corresponding written representations, so text processing must preserve letters and handle transliteration consistently." ], "standards_and_regulation": [ "The Unicode Standard, issued by the Unicode Consortium, specifies character encoding and normalization relevant to representing Montenegrin letters in digital text.", "ISO/IEC 10646, issued jointly by the International Organization for Standardization and the International Electrotechnical Commission, defines the universal coded character set used to encode its Latin and Cyrillic characters." ] }, "sources": [ { "id": "wikidata", "title": "Wikidata item Q3403931: Montenegrin alphabet", "url": "https://www.wikidata.org/wiki/Q3403931", "url_status": "live", "what_it_supports": "identity and sense of the item", "checked_by": "wikidata-api" }, { "id": "wikipedia-en", "title": "Wikipedia: Montenegrin alphabet", "url": "https://en.wikipedia.org/wiki/Montenegrin_alphabet", "url_status": "live", "what_it_supports": "general description of the item", "checked_by": "wikidata-api sitelink" } ], "structure": { "bundles": [ { "id": "montenegrin-alphabet-identity", "name": "Montenegrin alphabet identity", "description": "Establishes the registered alphabet's boundaries and the orthographic version being described.", "rationale": "The registry entry must encompass its script forms without conflating the alphabet with the language or competing historical proposals.", "layers": [ { "id": "script-coverage", "name": "Script coverage", "description": "Locates Latin and Cyrillic descriptions within the same alphabet model.", "findings": [ { "id": "paired-script-scope", "name": "Paired script scope", "description": "Record whether a source describes the Latin form, Cyrillic form or their relationship; a single-script source does not establish the other inventory.", "questions": [ { "text": "Does this source specify Montenegrin Latin, Montenegrin Cyrillic or both?", "kind": "boundary", "id": "paired-script-scope-q01" }, { "text": "What evidence identifies the inventory as Montenegrin rather than merely a shared regional repertoire?", "kind": "definition", "id": "paired-script-scope-q02" } ] } ] }, { "id": "orthographic-version", "name": "Orthographic version", "description": "Separates adopted descriptions, proposals and observed usage.", "findings": [ { "id": "version-qualified-inventory", "name": "Version-qualified inventory", "description": "Attach each inventory assertion to an identifiable edition and distinguish its stated authority from evidence of actual use.", "questions": [ { "text": "Which publication, edition and pages establish this letter inventory?", "kind": "provenance", "id": "version-qualified-inventory-q01" }, { "text": "Is this inventory an adopted standard, an earlier proposal or a description of usage?", "kind": "boundary", "id": "version-qualified-inventory-q02" } ] } ] } ] }, { "id": "letters-and-alphabetic-units", "name": "Letters and alphabetic units", "description": "Describes the units agents must recognise, count and compare in each script.", "rationale": "Montenegrin letter identity cannot be recovered reliably from code-point counts or generic Latin and Cyrillic character lists.", "layers": [ { "id": "distinctive-letters", "name": "Distinctive letters", "description": "Examines Ś and Ź and their Cyrillic correspondents as inventory members.", "findings": [ { "id": "acute-accent-letter-distinction", "name": "Acute-accent letter distinction", "description": "Track ś and ź separately from s and z, and с́ and з́ separately from с and з; record supported uppercase forms and source-defined sound correspondences.", "questions": [ { "text": "How does the selected orthographic edition define the names, case forms and sound values of these letters?", "kind": "definition", "id": "acute-accent-letter-distinction-q01" }, { "text": "Does the proposed inventory retain each acute-accent letter as a distinct alphabetic unit?", "kind": "measurement", "id": "acute-accent-letter-distinction-q02" } ] } ] }, { "id": "digraphs-and-order", "name": "Digraphs and order", "description": "Handles multi-character Latin letters and script-specific alphabetic positions.", "findings": [ { "id": "letter-count-versus-character-count", "name": "Letter count versus character count", "description": "Record the alphabetic status and position of Dž, Lj and Nj independently from their component characters and from the Cyrillic inventory's order.", "questions": [ { "text": "Which units does the source count as letters, and what total follows for each script?", "kind": "measurement", "id": "letter-count-versus-character-count-q01" }, { "text": "What order does the source assign to the digraph letters and to Ś and Ź?", "kind": "definition", "id": "letter-count-versus-character-count-q02" } ] } ] } ] }, { "id": "script-correspondence", "name": "Script correspondence", "description": "Defines how letter identities transfer between Montenegrin Latin and Cyrillic.", "rationale": "Script conversion must preserve distinctions and avoid accidentally making lexical or orthographic changes.", "layers": [ { "id": "conversion-mapping", "name": "Conversion mapping", "description": "Records case-sensitive correspondences between alphabetic units.", "findings": [ { "id": "letter-level-correspondence", "name": "Letter-level correspondence", "description": "Specify mappings for the full inventories, including Ś/Ź and digraph-to-single-letter correspondences, with separate treatment of uppercase and title case.", "questions": [ { "text": "What sourced mapping covers every letter in both conversion directions?", "kind": "provenance", "id": "letter-level-correspondence-q01" }, { "text": "How should Dž, DŽ, Lj, LJ, Nj and NJ be rendered when converting case-sensitive text?", "kind": "action", "id": "letter-level-correspondence-q02" } ] } ] }, { "id": "contextual-ambiguity", "name": "Contextual ambiguity", "description": "Identifies sequences requiring more than character substitution.", "findings": [ { "id": "digraph-and-spelling-boundaries", "name": "Digraph and spelling boundaries", "description": "Distinguish an alphabetic digraph from adjacent independent letters, and distinguish script conversion from replacing sj or zj with another spelling.", "questions": [ { "text": "When can a matching character sequence represent separate letters rather than one digraph letter?", "kind": "boundary", "id": "digraph-and-spelling-boundaries-q01" }, { "text": "What lexical or orthographic evidence is required before changing sj or zj to ś or ź?", "kind": "action", "id": "digraph-and-spelling-boundaries-q02" } ] } ] } ] }, { "id": "digital-letter-integrity", "name": "Digital letter integrity", "description": "Connects alphabetic identity to encoded text, rendering and input.", "rationale": "Combining accents and visually similar Latin and Cyrillic forms can cause silent loss or substitution.", "layers": [ { "id": "encoding-and-equivalence", "name": "Encoding and equivalence", "description": "Records valid representations and separates normalization from accent removal.", "findings": [ { "id": "combining-acute-representation", "name": "Combining acute representation", "description": "ICANN represents Cyrillic с́ and з́ using the corresponding Cyrillic base plus U+0301; its domain-label profile is evidence for encoding practice, not a complete orthographic authority. [ICANN reference rules](https://www.icann.org/sites/default/files/packages/lgr/lgr-second-level-montenegrin-cyrillic-language-24jan24-en.html)", "questions": [ { "text": "Which code-point sequences and normalization forms preserve each required Montenegrin letter?", "kind": "definition", "id": "combining-acute-representation-q01" }, { "text": "Does normalization preserve the acute accent and base script through a save-and-reload cycle?", "kind": "measurement", "id": "combining-acute-representation-q02" } ] } ] }, { "id": "input-and-rendering", "name": "Input and rendering", "description": "Assesses whether implementations support faithful entry and display.", "findings": [ { "id": "visible-and-stored-letter-agreement", "name": "Visible and stored letter agreement", "description": "Compare stored sequences with displayed letters, including accent placement, case forms and accidental substitution of visually similar characters from another script.", "questions": [ { "text": "Can the selected keyboard and font enter and display all required letters in both cases?", "kind": "measurement", "id": "visible-and-stored-letter-agreement-q01" }, { "text": "What correction preserves the original text when an accent is missing or a base character belongs to the wrong script?", "kind": "action", "id": "visible-and-stored-letter-agreement-q02" } ] } ] } ] }, { "id": "text-assessment-and-operations", "name": "Text assessment and operations", "description": "Constrains what agents may conclude from alphabet membership and what transformations they can justify.", "rationale": "A repertoire match does not identify a language, and useful search transformations may destroy distinctions needed for faithful text.", "layers": [ { "id": "repertoire-validation", "name": "Repertoire validation", "description": "Evaluates alphabet coverage without misclassifying whole documents.", "findings": [ { "id": "membership-with-context", "name": "Membership with context", "description": "Report whether letters fit the selected inventory while retaining context for foreign names, quotations, historical spellings and mixed-script passages.", "questions": [ { "text": "Which observed letters fall outside the selected Montenegrin inventory, and in which text spans?", "kind": "measurement", "id": "membership-with-context-q01" }, { "text": "What additional evidence is needed before labelling the text's language as Montenegrin?", "kind": "boundary", "id": "membership-with-context-q02" } ] } ] }, { "id": "sorting-search-and-preservation", "name": "Sorting, search and preservation", "description": "Makes operation-specific equivalence rules explicit.", "findings": [ { "id": "operation-specific-equivalence", "name": "Operation-specific equivalence", "description": "Keep exact letter identity, case-insensitive matching, cross-script matching and accent-insensitive discovery as separately declared operations.", "questions": [ { "text": "Which distinctions may this search or comparison operation ignore, and which must its results retain?", "kind": "action", "id": "operation-specific-equivalence-q01" }, { "text": "Do sorting and conversion checks preserve Ś/Ź, their Cyrillic counterparts and the intended digraph boundaries?", "kind": "measurement", "id": "operation-specific-equivalence-q02" } ] } ] } ] }, { "id": "evidence-and-external-alignment", "name": "Evidence and external alignment", "description": "What the world already says about this thing, gathered so the model can be checked against it.", "rationale": "A model that cannot be lined up against existing standards, identifiers and practice cannot be adopted by anyone who already uses them.", "layers": [ { "id": "reported-evidence", "name": "Reported evidence", "description": "Findings from the breadth pass, kept separate from the structural claims.", "findings": [ { "id": "evidence-confidence-notes", "name": "Check these first", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ "This is recalled knowledge, without source consultation.", "Check the authoritative orthographic publication and its edition before specifying adoption dates, issuing bodies or detailed spelling rules.", "The 32-letter count treats Latin digraphs as single alphabetic letters; it is not a count of Unicode code points." ], "questions": [ { "id": "evidence-confidence-notes-q01", "text": "Which of these check these first hold for the sense of Montenegrin alphabet this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-kinds", "name": "Kinds and varieties", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ "Montenegrin Latin alphabet", "Montenegrin Cyrillic alphabet" ], "questions": [ { "id": "evidence-kinds-q01", "text": "Which of these kinds and varieties hold for the sense of Montenegrin alphabet this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-identifiers", "name": "Identifiers and schemes", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ { "scheme": "ISO 15924", "value_or_pattern": "Latn", "note": "Identifies the Latin script, not specifically the Montenegrin alphabet." }, { "scheme": "ISO 15924", "value_or_pattern": "Cyrl", "note": "Identifies the Cyrillic script, not specifically the Montenegrin alphabet." }, { "scheme": "ISO 639-3", "value_or_pattern": "cnr", "note": "Identifies the Montenegrin language rather than either alphabet." } ], "questions": [ { "id": "evidence-identifiers-q01", "text": "Which of these identifiers and schemes hold for the sense of Montenegrin alphabet this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-standards-and-regulation", "name": "Standards and regulation", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ "The Unicode Standard, issued by the Unicode Consortium, provides character encoding for the letters and combining marks used in digital Montenegrin text." ], "questions": [ { "id": "evidence-standards-and-regulation-q01", "text": "Which of these standards and regulation hold for the sense of Montenegrin alphabet this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-real-world-use", "name": "Real-world use", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ "Writing Montenegrin in education, publishing, administration and personal communication.", "Transliteration between Latin and Cyrillic representations.", "Configuring keyboards, fonts, spellcheckers and text-search systems for Montenegrin." ], "questions": [ { "id": "evidence-real-world-use-q01", "text": "Which of these real-world use hold for the sense of Montenegrin alphabet this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-measurements", "name": "Typical measurements", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ { "quantity": "Letters in the standard alphabet", "typical_range": "32 in each script form", "unit": "letters" } ], "questions": [ { "id": "evidence-measurements-q01", "text": "Which of these typical measurements hold for the sense of Montenegrin alphabet this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-failure-modes-and-hazards", "name": "Failure modes and hazards", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ "Omitting or replacing the distinctive Latin letters ś and ź can erase intended spelling distinctions.", "Treating the Latin digraphs dž, lj and nj as two alphabetic units can produce incorrect alphabetic ordering or letter counts.", "Inadequate font or combining-mark support can render accented letters incorrectly.", "Search and comparison systems can mishandle visually identical text represented by different Unicode normalization forms." ], "questions": [ { "id": "evidence-failure-modes-and-hazards-q01", "text": "Which of these failure modes and hazards hold for the sense of Montenegrin alphabet this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-regional-variation", "name": "Regional variation", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ "Montenegrin is written in both Latin and Cyrillic; script choice varies with context and user preference.", "Its alphabets closely resemble those used for neighbouring South Slavic standards, but include two additional letters relative to the corresponding Serbian alphabets." ], "questions": [ { "id": "evidence-regional-variation-q01", "text": "Which of these regional variation hold for the sense of Montenegrin alphabet this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-neighbours", "name": "Neighbouring kinds and how to tell them apart", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ { "name": "Montenegrin language", "difference": "The language includes spoken grammar, vocabulary and pronunciation; the alphabet is its inventory of writing letters." }, { "name": "Montenegrin orthography", "difference": "Orthography governs spelling, capitalization and punctuation; the alphabet specifies letters and their order." }, { "name": "Serbian alphabet", "difference": "The corresponding standard Serbian alphabets have 30 letters; the Montenegrin alphabets have 32." }, { "name": "Latin script", "difference": "Latin is a script used by many languages; the Montenegrin Latin alphabet selects and orders letters for Montenegrin." }, { "name": "Cyrillic script", "difference": "Cyrillic is a script used by many languages; the Montenegrin Cyrillic alphabet is a language-specific inventory." } ], "questions": [ { "id": "evidence-neighbours-q01", "text": "Which of these neighbouring kinds and how to tell them apart hold for the sense of Montenegrin alphabet this model covers, and on what evidence?", "kind": "provenance" } ] } ] } ] } ] }, "openQuestions": [ "Which authoritative orthographic edition should anchor this model, and what later amendments, if any, must it incorporate?", "What exact inventories, letter names, case forms and alphabetic orders does that edition prescribe for both scripts?", "Under what lexical and normative conditions are ś/ź spellings and sj/zj sequences alternatives, distinct forms or impermissible substitutions?", "Which documented word-boundary or morpheme-boundary cases require contextual disambiguation of Dž, Lj and Nj during conversion?", "Which current collation, keyboard and font implementations demonstrably preserve the complete inventory, and where do their behaviours diverge from the cited orthography?" ], "statistics": { "bundles": 6, "layers": 11, "findings": 19, "questions": 29 } }