{ "model": { "rank": 1497, "code": "thing-q8097", "model_id": "vr.tr.telugu", "name": "Telugu", "purpose": "Enable an AI agent to recognise Telugu language use, assess whether its interpretation is reliable, and choose appropriate transcription, translation, localisation or review actions.", "family": "Thing Registry", "category": "Information and virtual systems", "status": "research-draft", "kind": "thing", "plane": "INF", "domain": "INF.MED", "industry": "", "version": "", "url": "/models/thing/q8097/", "tier": 2, "score": 143, "payload": { "layer": "wikidata", "aliases": [ "Hindu joint family", "Manna-Dora" ], "aliasCount": 2, "merged": 2, "knownIn": 143, "facets": null, "markers": [], "lexicalClass": "", "senseRank": null, "alsoRegisteredAs": null, "source": { "dataset": "wikidata", "item": "Q8097", "url": "https://www.wikidata.org/wiki/Q8097", "license": "CC0 1.0" } }, "research": { "vercy": "1.0-draft", "publication": { "status": "research-draft", "adjudicationStatus": "unreviewed", "publishableCanonical": false, "generatedAt": "2026-09-06T20:39:09Z", "providers": [ "Codex", "Grok" ], "missingProviders": [], "pass": 2, "cost": { "grok": { "usd": 0.01411884, "turns": 1, "seconds": 156.4, "error": null }, "codex_seconds": 74.5 } }, "metaModel": { "id": "THING-Q8097", "registryId": "vr.tr.telugu", "name": "Telugu", "version": "0.1.0-research.1", "entryKind": "thing", "family": "Thing Registry", "domain": [ "PHY.OBJ" ], "status": "research-draft" }, "canonicalUrl": "https://ver.cy/models/thing/q8097/", "model": { "registry_id": "vr.tr.telugu", "name": "Telugu", "purpose": "Enable an AI agent to recognise Telugu language use, assess whether its interpretation is reliable, and choose appropriate transcription, translation, localisation or review actions.", "definition": "Telugu is a South-Central Dravidian language (ISO 639-3 tel) of the eastern Deccan, written in the Telugu abugida (ISO 15924 Telu), used as the majority first language and a scheduled official language of Andhra Pradesh and Telangana, with a continuous record from early-medieval inscriptions through a modern standard based on coastal dialects.", "scope_statement": "Provisionally interpret vr.tr.telugu as the Telugu language and own the evidence needed to identify, interpret and process its spoken and written forms; the missing registry definition and PHY / PHY.OBJ placement leave the intended referent unresolved.", "in_scope": [ "Evidence that speech or text is Telugu, including mixed-language and romanised material", "Telugu variety, register and audience requirements relevant to interpretation", "Writing and pronunciation distinctions that affect Telugu meaning", "Telugu grammatical, lexical and contextual interpretation", "Readiness and limitations for Telugu transcription, translation and localisation" ], "out_of_scope": [ "Telugu people, ethnic identity and individual speaker biographies", "The Telugu script as an independent writing system with its complete character inventory", "Andhra Pradesh, Telangana and other geographic or administrative entities", "Physical manuscripts, books, recordings and storage devices as objects", "Individual literary works, films and their intellectual property records", "Language-processing software and datasets as independently managed products" ], "distinguishing_features": [ "Check whether the referent is a language rather than a person, community or physical artefact; the registry name alone does not resolve this boundary.", "Use language identifiers te and tel as supporting metadata, then check the actual content rather than treating its label as conclusive. These identifiers designate Telugu in the [Library of Congress language-code listing](https://www.loc.gov/standards/iso639-2/php/langcodes-keyword.php?SearchTerm=te&SearchType=iso_639_1).", "Distinguish Telugu-script recognition from Telugu-language recognition: require lexical or grammatical evidence, especially for quotations, names and very short strings.", "For confusion with Kannada, inspect character identity and linguistic evidence rather than rounded glyph appearance; Unicode explicitly notes similarities in script rendering. [Unicode Telugu script description](https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-12/)", "For Latin-script material, test whether the sequence admits a supported Telugu reading and whether surrounding language confirms it; Latin letters alone neither establish nor exclude Telugu." ], "characteristics": [ { "name": "Referent interpretation", "kind": "category", "unit_or_values": "Telugu language; Telugu script; community reference; physical artefact reference; unresolved", "why_it_matters": "Prevents a language model from silently absorbing a different thing suggested by the registry classification." }, { "name": "Language identification evidence", "kind": "state", "unit_or_values": "Confirmed by competent review; supported by contextual evidence; tentative; conflicting; insufficient", "why_it_matters": "Controls whether an agent can proceed with Telugu processing or must seek more context." }, { "name": "Representation", "kind": "category", "unit_or_values": "Speech; Telugu-script text; scheme-based romanisation; informal romanisation; mixed representation", "why_it_matters": "Determines the appropriate recognition, segmentation and conversion operations." }, { "name": "Variety attribution", "kind": "relation", "unit_or_values": "Relation to an evidenced regional, social or historical Telugu variety, with source and uncertainty", "why_it_matters": "Keeps unfamiliar but legitimate forms from being automatically corrected to another variety." }, { "name": "Register and address", "kind": "category", "unit_or_values": "Conversational; formal written; literary; technical; mixed; unknown, with observed address conventions", "why_it_matters": "Guides wording, politeness and preservation of the speaker's intended relationship to the audience." }, { "name": "Language mixing", "kind": "relation", "unit_or_values": "Links from identified spans to Telugu or another evidenced language; ambiguous spans retained", "why_it_matters": "Allows English or other embedded material to be handled without misclassifying the entire utterance." }, { "name": "Representation integrity", "kind": "state", "unit_or_values": "Verified; suspected OCR error; suspected encoding or shaping error; uncertain transcription; incomplete", "why_it_matters": "Separates damage introduced by processing from unusual Telugu spelling or expression." }, { "name": "Task-specific validation", "kind": "measurement", "unit_or_values": "Error count or rate on a named Telugu task and reference set, with segmentation method and variety coverage", "why_it_matters": "Makes readiness depend on relevant evidence rather than a generic multilingual capability claim." } ], "affordances": [ "Identify Telugu-bearing spans and retain uncertainty where script, metadata and linguistic evidence disagree.", "Transcribe Telugu speech while preserving uncertain sounds, names and language switches.", "Convert Telugu script and romanisation using a declared scheme and flag distinctions that cannot be recovered.", "Translate Telugu content while preserving negation, participant roles, address conventions and unresolved ambiguity.", "Adapt Telugu wording to an evidenced audience, variety and register.", "Diagnose Telugu text corruption and route uncertain or consequential interpretations to competent review." ] }, "sources": [ { "id": "krishnamurti-2003", "title": "The Dravidian Languages - Cambridge University Press (Bhadriraju Krishnamurti, 2003)", "url": "", "what_it_supports": "Genetic classification as South-Central Dravidian, historical stages, phonology, morphology, and the literary/spoken split." }, { "id": "census-india-2011-language", "title": "Census of India 2011, Language (Paper 1 of 2018) - Office of the Registrar General & Census Commissioner, India", "url": "", "what_it_supports": "First-language speaker count in India and rank among Indian languages." }, { "id": "iso-639-3-tel", "title": "ISO 639-3 code tel (Telugu) - SIL International", "url": "https://iso639-3.sil.org/code/tel", "what_it_supports": "Stable language identifier te/tel and distinction from related Dravidian codes.", "url_status": "live" }, { "id": "unicode-telugu-block", "title": "Unicode Telugu chart (U+0C00-U+0C7F) - Unicode Consortium", "url": "https://www.unicode.org/charts/PDF/U0C00.pdf", "what_it_supports": "Script identity, block range, and encoded character inventory.", "url_status": "live" }, { "id": "india-eighth-schedule", "title": "Constitution of India, Eighth Schedule - Government of India", "url": "", "what_it_supports": "Scheduled-language status of Telugu in the Union." } ], "structure": { "bundles": [ { "id": "telugu-identity-and-boundaries", "name": "Telugu identity and boundaries", "description": "Establish what Telugu denotes in this entry and what supports an identification of Telugu usage.", "rationale": "The registry supplies neither a definition nor a classification that clearly identifies a language.", "layers": [ { "id": "registry-referent", "name": "Registry referent", "description": "Separate the intended registered thing from its script, speakers and physical manifestations.", "findings": [ { "id": "intended-telugu-referent", "name": "Intended Telugu referent", "description": "Record the evidence for interpreting this entry as a language and preserve the unresolved classification conflict.", "questions": [ { "text": "Does the originating registry record mean the Telugu language, a Telugu person, the script or another referent?", "kind": "definition", "id": "intended-telugu-referent-q01" }, { "text": "Does an existing world model already own that same concept and therefore require this entry to link to it?", "kind": "boundary", "id": "intended-telugu-referent-q02" } ] } ] }, { "id": "language-recognition", "name": "Language recognition", "description": "Evaluate Telugu identity at the level of the actual speech or text.", "findings": [ { "id": "telugu-identification-basis", "name": "Telugu identification basis", "description": "Record linguistic evidence separately from language tags, script detection and source labels.", "questions": [ { "text": "Which words, constructions or contextual evidence support Telugu rather than Kannada, another language or an isolated proper name?", "kind": "definition", "id": "telugu-identification-basis-q01" }, { "text": "What additional context or competent review would resolve a short, romanised or conflicting sample?", "kind": "action", "id": "telugu-identification-basis-q02" } ] } ] } ] }, { "id": "telugu-variety-and-social-use", "name": "Telugu variety and social use", "description": "Capture the variety and communicative setting needed to interpret or produce suitable Telugu.", "rationale": "A single assumed Telugu norm can erase meaningful variation or produce inappropriate forms of address.", "layers": [ { "id": "variety-evidence", "name": "Variety evidence", "description": "Attribute regional, social or historical usage only as far as the evidence supports.", "findings": [ { "id": "supported-variety-attribution", "name": "Supported variety attribution", "description": "Record the provenance of a Telugu variety label and the observed forms supporting it.", "questions": [ { "text": "Which source or speaker description supports the proposed Telugu variety, and which features occur in the sample?", "kind": "provenance", "id": "supported-variety-attribution-q01" }, { "text": "Could the apparent regional difference instead reflect register, personal usage, historical spelling or transcription error?", "kind": "boundary", "id": "supported-variety-attribution-q02" } ] } ] }, { "id": "register-and-audience", "name": "Register and audience", "description": "Connect Telugu expression choices to the intended audience and relationship between participants.", "findings": [ { "id": "address-and-style-fit", "name": "Address and style fit", "description": "Record conversational, formal or literary expectations and the address choices that must be preserved.", "questions": [ { "text": "Which Telugu pronouns, titles and verb forms signal the intended familiarity, respect or number of addressees?", "kind": "definition", "id": "address-and-style-fit-q01" }, { "text": "Should the agent preserve the original register or adapt it to a specified audience, and who establishes that target?", "kind": "action", "id": "address-and-style-fit-q02" } ] } ] } ] }, { "id": "telugu-writing-and-speech", "name": "Telugu writing and speech", "description": "Preserve distinctions when Telugu moves between speech, script and romanisation.", "rationale": "An agent needs to distinguish Telugu content from errors caused by recognition, rendering or conversion.", "layers": [ { "id": "script-and-text-integrity", "name": "Script and text integrity", "description": "Assess whether the written representation preserves the intended Telugu sequence.", "findings": [ { "id": "telugu-character-sequence-integrity", "name": "Telugu character sequence integrity", "description": "Check vowel signs, virama and consonant combinations when diagnosing text corruption; Telugu rendering requires interpretation of character sequences. [Unicode Telugu script description](https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-12/)", "questions": [ { "text": "Does the underlying Telugu character sequence support the displayed reading, or has OCR, encoding or font shaping altered it?", "kind": "measurement", "id": "telugu-character-sequence-integrity-q01" }, { "text": "Which repairs can be supported by the original image or source text while retaining the unrepaired original?", "kind": "action", "id": "telugu-character-sequence-integrity-q02" } ] } ] }, { "id": "sound-and-romanisation", "name": "Sound and romanisation", "description": "Identify what a speech transcription or Latin-script representation preserves and loses.", "findings": [ { "id": "recoverable-telugu-distinctions", "name": "Recoverable Telugu distinctions", "description": "Record the transcription convention and unresolved sound-to-letter alternatives; a published reference option is the [ALA-LC Telugu romanisation table](https://loc.gov/catdir/cpso/romanization/telugu.pdf).", "questions": [ { "text": "Is the Latin text governed by a named Telugu romanisation scheme or by informal spelling, and which distinctions does it leave ambiguous?", "kind": "provenance", "id": "recoverable-telugu-distinctions-q01" }, { "text": "Which uncertain vowels or consonants require audio, context or speaker confirmation before converting the sample to Telugu script?", "kind": "action", "id": "recoverable-telugu-distinctions-q02" } ] } ] } ] }, { "id": "telugu-meaning-and-language-mixing", "name": "Telugu meaning and language mixing", "description": "Resolve the grammatical and lexical evidence required to interpret Telugu utterances.", "rationale": "Recognition of Telugu words alone does not establish participant roles, intended action or the treatment of embedded languages.", "layers": [ { "id": "grammatical-interpretation", "name": "Grammatical interpretation", "description": "Make consequential interpretations traceable to Telugu forms and their context.", "findings": [ { "id": "participants-and-predicate-meaning", "name": "Participants and predicate meaning", "description": "Record how word forms, suffixes and context support participant roles, negation and the interpretation of the predicate.", "questions": [ { "text": "Which Telugu forms establish who acts, who is affected and whether the statement is negated, questioned or requested?", "kind": "definition", "id": "participants-and-predicate-meaning-q01" }, { "text": "Which omitted participants or ambiguous forms require surrounding discourse before the agent can act on the utterance?", "kind": "boundary", "id": "participants-and-predicate-meaning-q02" } ] } ] }, { "id": "lexical-and-mixed-language-reading", "name": "Lexical and mixed-language reading", "description": "Interpret Telugu vocabulary alongside names, borrowed terms and language switches.", "findings": [ { "id": "telugu-span-and-term-treatment", "name": "Telugu span and term treatment", "description": "Record supported meanings and language boundaries without assuming every unfamiliar expression is foreign or erroneous.", "questions": [ { "text": "Is the disputed expression Telugu vocabulary, a proper name, a borrowed term or a switch into another language, and what evidence supports that reading?", "kind": "boundary", "id": "telugu-span-and-term-treatment-q01" }, { "text": "Should each name or technical term be retained, transliterated or translated for the specified Telugu audience?", "kind": "action", "id": "telugu-span-and-term-treatment-q02" } ] } ] } ] }, { "id": "telugu-task-readiness", "name": "Telugu task readiness", "description": "Determine which language operations are supported by the available evidence and validation.", "rationale": "Success on one Telugu representation or variety does not establish reliable performance on another.", "layers": [ { "id": "operation-selection", "name": "Operation selection", "description": "Match the requested transformation to the Telugu material and its unresolved distinctions.", "findings": [ { "id": "supported-transformation", "name": "Supported transformation", "description": "Record whether transcription, transliteration, translation or register adaptation can meet the requested fidelity.", "questions": [ { "text": "Which Telugu operation is requested, and must it preserve wording, pronunciation, meaning, address conventions or literary form?", "kind": "action", "id": "supported-transformation-q01" }, { "text": "Which ambiguities in the source prevent a unique output and must be retained as alternatives?", "kind": "boundary", "id": "supported-transformation-q02" } ] } ] }, { "id": "validation-and-review", "name": "Validation and review", "description": "Assess output quality against relevant Telugu examples and competent judgments.", "findings": [ { "id": "telugu-output-acceptability", "name": "Telugu output acceptability", "description": "Record task-specific errors, variety coverage and review findings before treating an output as ready for use.", "questions": [ { "text": "On representative Telugu samples, how often does the process alter names, negation, participant roles, address conventions or recoverable character distinctions?", "kind": "measurement", "id": "telugu-output-acceptability-q01" }, { "text": "Which unresolved errors require a reviewer competent in the relevant Telugu variety and subject before the result is used?", "kind": "action", "id": "telugu-output-acceptability-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-kinds", "name": "Kinds and varieties", "description": "Reported by the breadth pass; each item needs checking against its source before it becomes normative.", "evidence": [ "Standard / school-and-media Telugu (coastal Andhra prestige variety)", "Coastal Andhra (Krishna-Godavari) dialects", "Rayalaseema dialects", "Telangana dialects", "Uttarandhra / Northern Circars dialects", "Granthika (classical-literary written register)", "Vyavaharika (modern spoken and informal written register)", "Historical Telugu (Old and Middle Telugu of inscriptions and pre-modern literature)" ], "questions": [ { "id": "evidence-kinds-q01", "text": "Which of these kinds and varieties hold for the sense of Telugu this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-identifiers", "name": "Identifiers and schemes", "description": "Reported by the breadth pass; each item needs checking against its source before it becomes normative.", "evidence": [ { "scheme": "Wikidata", "value_or_pattern": "Q8097", "note": "Telugu language (not the ethnonym)." }, { "scheme": "ISO 639-1", "value_or_pattern": "te", "note": "Two-letter language code." }, { "scheme": "ISO 639-2 / ISO 639-3", "value_or_pattern": "tel", "note": "Three-letter bibliographic and individual-language code." }, { "scheme": "BCP 47", "value_or_pattern": "te", "note": "Language subtag; region variants such as te-IN." }, { "scheme": "ISO 15924", "value_or_pattern": "Telu (340)", "note": "Telugu script, distinct from the language code." }, { "scheme": "Glottolog", "value_or_pattern": "telu1262", "note": "Languoid identifier for Telugu." }, { "scheme": "Unicode", "value_or_pattern": "U+0C00-U+0C7F", "note": "Telugu block; script property Telugu." } ], "questions": [ { "id": "evidence-identifiers-q01", "text": "Which of these identifiers and schemes hold for the sense of Telugu this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-standards-and-regulation", "name": "Standards and regulation", "description": "Reported by the breadth pass; each item needs checking against its source before it becomes normative.", "evidence": [ "ISO 639-1/2/3 language codes te / tel - ISO and SIL International (ISO 639-3 registration authority)", "ISO 15924 script code Telu (340) - ISO", "The Unicode Standard, Telugu block U+0C00-U+0C7F - Unicode Consortium", "IS 13194:1991 Indian Script Code for Information Interchange (ISCII) - Bureau of Indian Standards", "Constitution of India, Eighth Schedule (Telugu as a scheduled language) - Government of India", "Declaration of Telugu as a classical language of India (2008) - Government of India", "Andhra Pradesh Official Language Act, 1966 - Government of Andhra Pradesh", "State official-language policy of Telangana (Telugu, with Urdu as an additional official language) - Government of Telangana" ], "questions": [ { "id": "evidence-standards-and-regulation-q01", "text": "Which of these standards and regulation hold for the sense of Telugu this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-real-world-use", "name": "Real-world use", "description": "Reported by the breadth pass; each item needs checking against its source before it becomes normative.", "evidence": [ "Official language of administration, courts at the state level, and public education in Andhra Pradesh and Telangana, and in the Puducherry enclave of Yanam.", "Home language and interethnic lingua franca across coastal Andhra, Rayalaseema, and Telangana, including large urban centres such as Hyderabad, Visakhapatnam, Vijayawada, and Tirupati.", "Medium of a major film, television, newspaper, and web industry (often called Tollywood for cinema).", "Liturgical, commentarial, and literary language in Vaishnava, Shaiva, and court traditions from the Kakatiya and Vijayanagara periods onward.", "Software, mobile, and government localization locale (te / te-IN), including Unicode text entry, fonts, and CLDR locale data.", "Heritage and community language among diaspora populations in the United States, the Gulf, Singapore, Malaysia, Fiji, Mauritius, and South Africa." ], "questions": [ { "id": "evidence-real-world-use-q01", "text": "Which of these real-world use hold for the sense of Telugu this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-measurements", "name": "Typical measurements", "description": "Reported by the breadth pass; each item needs checking against its source before it becomes normative.", "evidence": [ { "quantity": "First-language speakers (India, 2011 census; later global estimates)", "typical_range": "81-96 million", "unit": "speakers" }, { "quantity": "Share of India's population reporting Telugu as mother tongue (2011)", "typical_range": "about 6.7", "unit": "percent" }, { "quantity": "Traditional orthographic inventory (aksharamala)", "typical_range": "16 vowels + 36 consonants", "unit": "letters" }, { "quantity": "Unicode Telugu block size", "typical_range": "128", "unit": "code points" } ], "questions": [ { "id": "evidence-measurements-q01", "text": "Which of these typical measurements hold for the sense of Telugu this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-failure-modes-and-hazards", "name": "Failure modes and hazards", "description": "Reported by the breadth pass; each item needs checking against its source before it becomes normative.", "evidence": [ "Diglossia between granthika (literary) and vyavaharika (spoken) forms, which can impede school literacy when teaching materials stay close to the classical register.", "Text encoding and font-shaping failures (legacy ISCII, unshaped conjuncts, dotted-circle virama display) that corrupt names, records, and search.", "Stigmatization of Telangana and some Rayalaseema speech in older broadcast and film standards, producing social exclusion rather than mutual-unintelligibility.", "Language shift toward English in urban professional and diaspora settings, with attrition of literacy in Telugu script.", "OCR and NLP confusion with visually similar Kannada-script glyphs.", "Political instrumentalization of dialect and state identity after the Andhra Pradesh-Telangana bifurcation." ], "questions": [ { "id": "evidence-failure-modes-and-hazards-q01", "text": "Which of these failure modes and hazards hold for the sense of Telugu this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-regional-variation", "name": "Regional variation", "description": "Reported by the breadth pass; each item needs checking against its source before it becomes normative.", "evidence": [ "Telangana speech carries a heavier Dakhni Urdu/Persian loan stratum and some distinct verb and pronoun forms relative to coastal Andhra.", "Coastal Andhra (especially Krishna-Godavari) supplies the prestige standard for education, news, and cinema.", "Rayalaseema varieties show Kannada contact effects and are often treated as a third major regional grouping.", "Uttarandhra / Northern Circars speech shows Odia and, locally, tribal-language contact.", "Tamil Nadu, Karnataka, Odisha, and Yanam communities maintain Telugu with local bilingualism; diaspora varieties add English and host-language mixing." ], "questions": [ { "id": "evidence-regional-variation-q01", "text": "Which of these regional variation hold for the sense of Telugu this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-neighbours", "name": "Neighbouring kinds and how to tell them apart", "description": "Reported by the breadth pass; each item needs checking against its source before it becomes normative.", "evidence": [ { "name": "Kannada", "difference": "Related but not mutually intelligible Dravidian language (ISO 639-3 kan; script Knda). Test: basic lexicon and verb morphology (e.g. Telugu illu 'house' vs Kannada mane) and ISO/script codes; the two scripts share a medieval ancestor and look similar but encode different languages." }, { "name": "Tamil", "difference": "Southern Dravidian neighbour (ISO 639-3 tam), not mutually intelligible, written in Tamil script. Test: language code, script, and core pronouns/lexicon (Telugu nēnu 'I' vs Tamil nāṉ)." }, { "name": "Gondi and other South-Central Dravidian languages", "difference": "Genetically closer than Tamil or Kannada, but separate languages without the Telugu literary standard. Test: ISO 639-3 (e.g. gon and related codes) and absence of Telugu-script literacy as the community norm." }, { "name": "Odia", "difference": "Indo-Aryan neighbour in northern coastal Andhra, not Dravidian. Test: language family and ISO 639-3 ori/or." }, { "name": "Telugu people (ethnonym)", "difference": "An ethnic/regional identity, not the language. Test: a person may identify as Telugu by ancestry while reporting another mother tongue, or speak Telugu as L1 without that ethnic label; Wikidata Q8097 is the language." }, { "name": "Telugu script", "difference": "The writing system (ISO 15924 Telu), which can in principle record other languages. Test: script code Telu vs language code tel; spoken Telugu exists independently of literacy in the script." } ], "questions": [ { "id": "evidence-neighbours-q01", "text": "Which of these neighbouring kinds and how to tell them apart hold for the sense of Telugu this model covers, and on what evidence?", "kind": "provenance" } ] } ] } ] } ] }, "openQuestions": [ "Does vr.tr.telugu intentionally denote the Telugu language, and what explains its PHY / PHY.OBJ classification?", "Does an existing Vercy world model already cover the intended concept and require a registry link instead of a separate publication?", "Which regional, social and historical Telugu varieties must the first researched model cover, and which sources establish their boundaries?", "Which authorities and audience-specific conventions should govern Telugu spelling, romanisation, terminology and register adaptation?", "What representative Telugu evaluation material and acceptance criteria are available for speech, script, informal romanisation and mixed-language processing?" ], "statistics": { "bundles": 6, "layers": 11, "findings": 18, "questions": 28 } }, "draft": { "generator": "vr.draft.v3", "status": "draft-generated", "researched": false, "archetype": "work, medium or creative form", "method": "Written from the archetype playbook - what this kind of thing needs beyond identity and provenance - and from the structure that recurred across 6,333 models already researched by two engines. Applied to this entry by rule. No source was read for this thing and no claim here is researched. This entry carries no facets of its own, so they were inferred from its domain - a guess about a whole domain applied to one thing.", "facetsInferred": true, "nextPass": "A researcher replaces this draft with a sourced specification. Treat every sentence below as a proposal to argue with.", "purpose": "Give an agent a durable, checkable way to recognise a Telugu, record what state it is in, and decide what may be done with it.", "whatItIs": "Enable an AI agent to recognise Telugu language use, assess whether its interpretation is reliable, and choose appropriate transcription, translation, localisation or review actions.", "characteristics": { "substance": "information", "origin": "conceptual", "agency": "inert" }, "whatYouCanDoWithIt": [ "read and interpreted", "observed and measured" ], "distinguishingFeatures": [ "Names folded into this entry, which a task may need to split apart again: Hindu joint family, Manna-Dora.", "2 finer distinctions are held as aliases rather than separate entries, because telling them apart needs a task that asks for it.", "Described in 143 Wikipedia languages, which is a measure of how widely the thing is known, not of how important it is." ], "openQuestionsForResearch": [ "Which of the bundles below does a real task actually need, and which are ceremony?", "What does this thing have that the facets do not capture at all?", "Which neighbouring kind is most often confused with a Telugu, and on what evidence are they told apart?" ], "whatItIsMadeOf": "content that has to be carried by something else", "physicalCharacter": [ "Does nothing on its own; everything it does, something else did to it.", "These come from the domain this entry sits in rather than from the entry itself, so treat them as a first guess about the whole domain applied to one thing." ], "whatCanBeDoneWithIt": [ "read it and act on what it says", "observe it, measure it, record its state" ], "howItIsRecognised": [ "What is seen is a copy or a performance, not the work. Recognising the work means recognising the content through whatever is carrying it." ], "relatedModels": [ { "relation": "covers", "note": "Finer kinds folded into this entry because telling them apart needs a task that asks for it. Each is a model waiting to be split out when one does.", "targets": [ "Hindu joint family", "Manna-Dora" ] } ], "standing": "Described in 143 Wikipedia languages, which measures how widely it is written about rather than how important or how common it is. 2 finer distinctions are held inside this entry as names rather than as separate models.", "structure": { "bundles": [ { "id": "identity-and-classification", "name": "Identity, naming and classification", "description": "How an agent tells one Telugu from another, and a Telugu from things that resemble it.", "rationale": "Recognition comes before every other claim. Without stable identity nothing else in the model can be trusted to be about the same thing twice.", "layers": [ { "id": "naming-and-identifiers", "name": "Names and identifiers", "description": "The names this thing goes by and the identifiers that survive translation and time.", "findings": [ { "id": "preferred-name-and-aliases", "name": "Preferred name, aliases and local names", "description": "Which name to use, which names mean the same thing, and which merely sound similar.", "questions": [ { "id": "preferred-name-and-aliases-q01", "text": "What identifies and describes the name of a Telugu, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "preferred-name-and-aliases-q02", "text": "Who or what asserted this about the name of a Telugu, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "preferred-name-and-aliases-q03", "text": "What may an agent decide or do once the name of a Telugu is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] }, { "id": "stable-identifiers", "name": "Stable identifiers and external keys", "description": "Identifiers that keep pointing at this kind of thing across systems and languages.", "questions": [ { "id": "stable-identifiers-q01", "text": "What identifies and describes an identifier for a Telugu, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "stable-identifiers-q02", "text": "Who or what asserted this about an identifier for a Telugu, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "stable-identifiers-q03", "text": "What may an agent decide or do once an identifier for a Telugu is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] }, { "id": "classification-and-granularity", "name": "Classification and granularity", "description": "Where a Telugu sits among kinds, and how finely a task needs to cut it.", "findings": [ { "id": "kind-and-parents", "name": "Kind, parents and neighbouring kinds", "description": "The classes this thing belongs to and the ones it is next to.", "questions": [ { "id": "kind-and-parents-q01", "text": "What identifies and describes the kind of a Telugu, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "kind-and-parents-q02", "text": "Who or what asserted this about the kind of a Telugu, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "kind-and-parents-q03", "text": "What may an agent decide or do once the kind of a Telugu is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] }, { "id": "distinguishing-features", "name": "Distinguishing features", "description": "What separates a Telugu from the things most often confused with it.", "questions": [ { "id": "distinguishing-features-q01", "text": "What identifies and describes what distinguishes a Telugu, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "distinguishing-features-q02", "text": "Who or what asserted this about what distinguishes a Telugu, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "distinguishing-features-q03", "text": "What may an agent decide or do once what distinguishes a Telugu is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] } ] }, { "id": "state-and-lifecycle", "name": "State and lifecycle", "description": "The states a Telugu passes through and the events that move it between them.", "rationale": "Most decisions about a thing depend on what state it is in now, which is a claim with a time on it, not a property.", "layers": [ { "id": "lifecycle-stages", "name": "Lifecycle stages", "description": "From coming into existence to ceasing to be one of these.", "findings": [ { "id": "stages-and-transitions", "name": "Stages and transitions", "description": "The stages worth naming and what moves a Telugu between them.", "questions": [ { "id": "stages-and-transitions-q01", "text": "What identifies and describes the lifecycle of a Telugu, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "stages-and-transitions-q02", "text": "Who or what asserted this about the lifecycle of a Telugu, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "stages-and-transitions-q03", "text": "What may an agent decide or do once the lifecycle of a Telugu is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] }, { "id": "observations-and-status", "name": "Observations and current status", "description": "What is observed about a Telugu, how often and by whom.", "findings": [ { "id": "observation-record", "name": "Observation record", "description": "How an observation of a Telugu is recorded so that it can be superseded rather than overwritten.", "questions": [ { "id": "observation-record-q01", "text": "What identifies and describes an observation of a Telugu, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "observation-record-q02", "text": "Who or what asserted this about an observation of a Telugu, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "observation-record-q03", "text": "What may an agent decide or do once an observation of a Telugu is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] } ] }, { "id": "content-and-access", "name": "Content, encoding and access", "description": "What a Telugu says, how it is encoded and who may read it.", "rationale": "An informational thing carries content that can be copied, versioned and withheld, none of which its physical carrier explains.", "layers": [ { "id": "content-and-encoding", "name": "Content and encoding", "description": "The content itself, its format and its language.", "findings": [ { "id": "content-and-format", "name": "Content, format and language", "description": "What a Telugu contains and in what form it is held.", "questions": [ { "id": "content-and-format-q01", "text": "What identifies and describes the content of a Telugu, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "content-and-format-q02", "text": "Who or what asserted this about the content of a Telugu, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "content-and-format-q03", "text": "What may an agent decide or do once the content of a Telugu is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] }, { "id": "access-and-rights", "name": "Access, rights and retention", "description": "Who may read, copy or change it, and for how long it is kept.", "findings": [ { "id": "access-rules", "name": "Access rules and retention", "description": "The permissions attached to a Telugu and the period it survives.", "questions": [ { "id": "access-rules-q01", "text": "What identifies and describes access to a Telugu, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "access-rules-q02", "text": "Who or what asserted this about access to a Telugu, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "access-rules-q03", "text": "What may an agent decide or do once access to a Telugu is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] } ] }, { "id": "work-and-manifestation", "name": "Work, version and copy", "description": "Which level of Telugu a statement is about.", "rationale": "The work, the edition, the file and the copy in hand are four things; rights and content attach to different ones.", "layers": [ { "id": "levels", "name": "Levels of the thing", "description": "Work, expression, manifestation and item, in plain terms.", "findings": [ { "id": "level-rules", "name": "What belongs at each level", "description": "Which facts hold for the work and which only for one copy.", "questions": [ { "id": "level-rules-q01", "text": "For Telugu, which facts belong to the work itself, which to a version, and which to a single copy?", "kind": "boundary" }, { "id": "level-rules-q02", "text": "What identifier exists at each level, and which one is being cited?", "kind": "definition" } ] } ] }, { "id": "versions", "name": "Versions, editions and variants", "description": "How versions differ and which is canonical to whom.", "findings": [ { "id": "version-record", "name": "Versions and canonicity", "description": "Differences that matter and who calls one authoritative.", "questions": [ { "id": "version-record-q01", "text": "Which versions or editions of Telugu exist, and how do they differ substantively?", "kind": "definition" }, { "id": "version-record-q02", "text": "Who treats which version as authoritative, and for what purpose?", "kind": "provenance" } ] } ] } ] }, { "id": "authorship-and-rights", "name": "Authorship, rights and permitted use", "description": "Who made Telugu and what may be done with it.", "rationale": "Rights are jurisdictional, time-limited and attached to a level, and an agent that ignores that will copy what it may not.", "layers": [ { "id": "authorship", "name": "Authorship and contribution", "description": "Who contributed what, and in what capacity.", "findings": [ { "id": "contribution-record", "name": "Contributors and roles", "description": "The people and bodies behind it, with their roles.", "questions": [ { "id": "contribution-record-q01", "text": "Who authored or contributed to Telugu, in what roles, and how is that attested?", "kind": "provenance" }, { "id": "contribution-record-q02", "text": "Where authorship is disputed or anonymous, what is recorded instead?", "kind": "boundary" } ] } ] }, { "id": "rights", "name": "Rights and permissions", "description": "Which rights subsist, where, until when, and what they permit.", "findings": [ { "id": "rights-record", "name": "Rights, term and permitted acts", "description": "The regime in force and what it allows.", "questions": [ { "id": "rights-record-q01", "text": "What rights subsist in Telugu, in which jurisdictions, and until when?", "kind": "definition" }, { "id": "rights-record-q02", "text": "Which acts are permitted without further permission, and which must an agent refuse?", "kind": "action" } ] } ] } ] }, { "id": "provenance-and-evidence", "name": "Provenance, evidence and time", "description": "Where every claim about a Telugu came from and when it held.", "rationale": "A claim without a source and a time cannot be superseded, only overwritten, and an agent that overwrites loses the ability to explain itself.", "layers": [ { "id": "source-and-authority", "name": "Source and authority", "description": "Who said it, on what evidence, and how strongly.", "findings": [ { "id": "claim-provenance", "name": "Claim provenance and confidence", "description": "The authority behind each claim about a Telugu and how confident it is.", "questions": [ { "id": "claim-provenance-q01", "text": "What identifies and describes a claim about a Telugu, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "claim-provenance-q02", "text": "Who or what asserted this about a claim about a Telugu, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "claim-provenance-q03", "text": "What may an agent decide or do once a claim about a Telugu is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] }, { "id": "time-and-versions", "name": "Time, versions and supersession", "description": "When a claim was true, when it was learnt, and what replaced it.", "findings": [ { "id": "validity-and-supersession", "name": "Validity period and supersession", "description": "How an old claim about a Telugu is retired without being erased.", "questions": [ { "id": "validity-and-supersession-q01", "text": "What identifies and describes the validity of a claim about a Telugu, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "validity-and-supersession-q02", "text": "Who or what asserted this about the validity of a claim about a Telugu, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "validity-and-supersession-q03", "text": "What may an agent decide or do once the validity of a claim about a Telugu is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] } ] } ] }, "statistics": { "bundles": 6, "layers": 12, "findings": 14, "questions": 38 } } } }