{ "model": { "rank": 5239, "code": "thing-q189223", "model_id": "vr.tr.turing-test", "name": "Turing test", "purpose": "Enable an AI agent to recognise a Turing-test proposal or trial, assess what its conversational evidence supports, and determine which conclusions or further evaluations are warranted.", "family": "Thing Registry", "category": "Activities and processes", "status": "research-draft", "kind": "thing", "plane": "ACT", "domain": "ACT.ACT", "industry": "", "version": "", "url": "/models/thing/q189223/", "tier": 2, "score": 69, "payload": { "layer": "wikidata", "aliases": [], "aliasCount": 0, "merged": 0, "knownIn": 69, "facets": null, "markers": [], "lexicalClass": "", "senseRank": null, "alsoRegisteredAs": null, "source": { "dataset": "wikidata", "item": "Q189223", "url": "https://www.wikidata.org/wiki/Q189223", "license": "CC0 1.0" } }, "research": { "vercy": "1.0-draft", "publication": { "status": "research-draft", "adjudicationStatus": "unreviewed", "publishableCanonical": false, "generatedAt": "2026-09-09T21:57:31Z", "providers": [ "Codex" ], "breadth": "recalled by Codex without web access - no source was read", "missingProviders": [], "pass": 2, "cost": { "grok": { "seconds": 22.8, "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: 01a0882c-1404-71e2-8173-759fa8233245\n--------\nuser\nDescribe what is already known about one registered thing. Answer as JSON only, no prose around it.\n\nThing: Turing test\nSense to describe: (none recorded)\nDomain code: ACT.ACT\nAlso known as: (none)\n\n\nContext for this batch of 1001 things:\n# Batch 005: 1001 reg", "usd": 0, "recall": true }, "codex": { "seconds": 66.7, "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: 01a0882c-1401-72f2-9f29-922377d9d2e2\n--------\nuser\nYou are drafting a Vercy meta-model for one registered thing. Answer as JSON only, no prose around it.\n\nThing: Turing test\nRegistry id: vr.tr.turing-test\nPlane / domain: ACT / ACT.ACT\nRegistry definition: (none recorded)\nNames folded into this entry: (none)\n\n\n" } } }, "metaModel": { "id": "THING-Q189223", "registryId": "vr.tr.turing-test", "name": "Turing test", "version": "0.1.0-research.1", "entryKind": "thing", "family": "Thing Registry", "domain": [ "ACT.ACT" ], "status": "research-draft" }, "canonicalUrl": "https://ver.cy/models/thing/q189223/", "model": { "registry_id": "vr.tr.turing-test", "name": "Turing test", "purpose": "Enable an AI agent to recognise a Turing-test proposal or trial, assess what its conversational evidence supports, and determine which conclusions or further evaluations are warranted.", "definition": "The Turing test is a family of behavioural tests derived from Alan Turing's imitation game, in which a machine's conversational performance is assessed by whether human judges can distinguish it from a human interlocutor under specified conditions.", "scope_statement": "This model owns the Turing test as a contested approach to evaluating machine intelligence through human judgments of conversational indistinguishability, including attributed interpretations, protocol variants, trial evidence and limits of inference; it distinguishes the test concept from individual implementations.", "in_scope": [ "Definitions and interpretations of the Turing test, with their proponents and disagreements", "Imitation-game roles, communication restrictions and human comparison conditions", "Operational protocols, judgment rules and protocol-specific passing criteria", "Trial records, judge decisions, uncertainty and reproducibility", "Claims about intelligence or understanding made from test outcomes" ], "out_of_scope": [ "General theories of intelligence, consciousness or personhood beyond their relationship to interpreting this test", "Machine architectures, training procedures and datasets except where they affect a trial's validity", "CAPTCHAs and automated bot-detection systems as independently modelled mechanisms", "General AI capability benchmarks without human-versus-machine conversational judgment", "Embodied or perceptual intelligence evaluations beyond documenting their relationship to Turing-test variants" ], "distinguishing_features": [ "A core conversational instance asks human judges to assess whether an interlocutor is human or machine; scoring answer correctness alone does not establish a Turing test.", "The protocol restricts identity-revealing channels so that judgments depend on the permitted interaction rather than direct inspection of the participant.", "A claimed pass must refer to a specified protocol, judgment rule and population; the label alone supplies no universal passing threshold.", "Human conversational performance supplies the comparison target, unlike benchmarks defined solely by task accuracy or expert solutions.", "The model distinguishes evidence of successful conversational imitation from additional claims about intelligence, understanding or consciousness." ], "characteristics": [ { "name": "Interpretive position", "kind": "category", "unit_or_values": "Attributed position: operational criterion of intelligence, evidence relevant to intelligence, conversational imitation benchmark, or other explicitly defined interpretation", "why_it_matters": "Different interpretations license different conclusions from the same trial outcome." }, { "name": "Protocol lineage", "kind": "relation", "unit_or_values": "Relationship to an identified formulation, publication or implemented variant", "why_it_matters": "The name Turing test can conceal substantive differences in roles, channels and decision rules." }, { "name": "Participant arrangement", "kind": "category", "unit_or_values": "Paired human-machine comparison, single-interlocutor classification, or another explicitly documented arrangement", "why_it_matters": "Participant arrangement changes the judgment task and its comparison baseline." }, { "name": "Interaction budget", "kind": "measurement", "unit_or_values": "Minutes per encounter and/or permitted conversational turns", "why_it_matters": "Brief exchanges and sustained questioning expose different opportunities for discrimination." }, { "name": "Permitted communication", "kind": "category", "unit_or_values": "Text-only or specified additional modalities, including timing and metadata visibility", "why_it_matters": "Available cues determine whether judges assess conversational behaviour or other identifying signals." }, { "name": "Judge population", "kind": "relation", "unit_or_values": "Defined recruitment population with language, relevant expertise and prior exposure", "why_it_matters": "Results depend on who judges and what those judges know about the task." }, { "name": "Machine-as-human judgment rate", "kind": "measurement", "unit_or_values": "Proportion of eligible machine encounters classified as human, with denominator and uncertainty", "why_it_matters": "This records a common outcome without treating it as sufficient evidence of passing every variant." }, { "name": "Human-as-human judgment rate", "kind": "measurement", "unit_or_values": "Proportion of eligible human encounters classified as human, with denominator and uncertainty", "why_it_matters": "Human controls reveal judge behaviour and conditions that make even human participants appear machine-like." }, { "name": "Passing rule", "kind": "category", "unit_or_values": "Explicit metric, threshold, aggregation method and treatment of abstentions, or no passing rule specified", "why_it_matters": "A verdict cannot be assessed independently of the rule that produced it." }, { "name": "Trial assessment state", "kind": "state", "unit_or_values": "Proposed, running, completed but unassessed, assessable, inconclusive, or invalid under the stated protocol", "why_it_matters": "Completion of an interaction does not establish that its evidence supports a verdict." } ], "affordances": [ "Classify a proposed evaluation as a core conversational Turing test, a documented extension or a neighbouring benchmark.", "Compare two implementations and identify protocol differences that prevent direct comparison of their results.", "Check that judge instructions, communication restrictions and passing rules are specified before interpreting outcomes.", "Assess a claimed pass against trial records, human controls and the declared decision rule.", "Identify additional trials or controls needed to resolve uncertainty about conversational indistinguishability.", "Constrain reports to the tested conditions and distinguish observed performance from philosophical interpretation." ] }, "sources": [], "structure": { "bundles": [ { "id": "meaning-and-interpretation", "name": "Meaning and interpretation", "description": "Records which Turing-test concept is intended and what significance its proponents assign to performance.", "rationale": "An agent must not silently substitute one interpretation of this contested concept for another.", "layers": [ { "id": "formulation-and-lineage", "name": "Formulation and lineage", "description": "Identifies the formulation being modelled and its relationship to other imitation-game formulations.", "findings": [ { "id": "attributed-test-definition", "name": "Attributed test definition", "description": "Record an attributed definition and the roles and judgment task it specifies; historical and later formulations require explicit comparison.", "questions": [ { "text": "Which source and author define the version of the Turing test used here?", "kind": "provenance", "id": "attributed-test-definition-q01" }, { "text": "What must the interrogator distinguish, and which participants occupy each role?", "kind": "definition", "id": "attributed-test-definition-q02" } ] } ] }, { "id": "contested-significance", "name": "Contested significance", "description": "Separates agreement about a procedure from disagreement about what its success means.", "findings": [ { "id": "intelligence-claim", "name": "Intelligence claim", "description": "Record whether a position treats passing as a definition, sufficient condition, necessary condition or limited evidence of intelligence, together with attributed objections.", "questions": [ { "text": "Who holds the stated relationship between passing and intelligence, and how do they justify it?", "kind": "provenance", "id": "intelligence-claim-q01" }, { "text": "Would this position allow an intelligent system to fail or a system without understanding to pass?", "kind": "boundary", "id": "intelligence-claim-q02" } ] } ] } ] }, { "id": "imitation-game-design", "name": "Imitation-game design", "description": "Defines the conversational encounter that gives a trial its identity.", "rationale": "Roles, channels and conversational constraints determine which discrimination task was actually tested.", "layers": [ { "id": "roles-and-comparison", "name": "Roles and comparison", "description": "Specifies judges, machine interlocutors, human controls and the information given to each.", "findings": [ { "id": "judge-task-and-human-control", "name": "Judge task and human control", "description": "Record whether judges compare participants or classify separate encounters, including disclosed machine prevalence and human-control instructions.", "questions": [ { "text": "Do judges choose between paired participants or classify each interlocutor independently?", "kind": "definition", "id": "judge-task-and-human-control-q01" }, { "text": "What are judges told about participant identities, machine prevalence and the purpose of the interaction?", "kind": "measurement", "id": "judge-task-and-human-control-q02" }, { "text": "What are human controls instructed to do, and how closely do their conditions match the machine's?", "kind": "measurement", "id": "judge-task-and-human-control-q03" } ] } ] }, { "id": "conversation-envelope", "name": "Conversation envelope", "description": "Records the channels, duration, topics and assistance available during an encounter.", "findings": [ { "id": "permitted-behaviour-and-cues", "name": "Permitted behaviour and cues", "description": "Make the interaction limits explicit, including personas, topic restrictions, external tools, response timing and visible metadata.", "questions": [ { "text": "Which modalities, topics, time limits and turn limits define the permitted conversation?", "kind": "definition", "id": "permitted-behaviour-and-cues-q01" }, { "text": "Which tools, human assistance, personas or response transformations are permitted for each participant?", "kind": "boundary", "id": "permitted-behaviour-and-cues-q02" }, { "text": "Could formatting, latency or interface metadata reveal identity independently of conversational content?", "kind": "measurement", "id": "permitted-behaviour-and-cues-q03" } ] } ] } ] }, { "id": "judgment-and-verdict", "name": "Judgment and verdict", "description": "Connects individual judge responses to a defensible protocol-specific outcome.", "rationale": "A headline passing claim is uninterpretable without its scoring rule, human comparison and uncertainty.", "layers": [ { "id": "decision-rule", "name": "Decision rule", "description": "Defines how classification, confidence and abstention responses become reported outcomes.", "findings": [ { "id": "declared-passing-criterion", "name": "Declared passing criterion", "description": "Record the chosen success criterion and when it was fixed, without assuming every Turing-test variant shares it.", "questions": [ { "text": "What exact metric, threshold and aggregation rule determine a pass?", "kind": "definition", "id": "declared-passing-criterion-q01" }, { "text": "Was the rule fixed before outcomes were inspected, and where is that version recorded?", "kind": "provenance", "id": "declared-passing-criterion-q02" }, { "text": "How are uncertain judgments, abstentions and incomplete encounters counted?", "kind": "measurement", "id": "declared-passing-criterion-q03" } ] } ] }, { "id": "outcome-and-uncertainty", "name": "Outcome and uncertainty", "description": "Records machine and human outcomes with the statistical context needed to interpret them.", "findings": [ { "id": "comparative-judgment-evidence", "name": "Comparative judgment evidence", "description": "Preserve outcome counts, denominators, judge-level dependence and uncertainty rather than only a passing percentage.", "questions": [ { "text": "How often were machine and human interlocutors each classified as human, and over how many eligible encounters?", "kind": "measurement", "id": "comparative-judgment-evidence-q01" }, { "text": "How do uncertainty estimates account for repeated judges, repeated systems and participant assignment?", "kind": "measurement", "id": "comparative-judgment-evidence-q02" }, { "text": "Does the evidence support the stated criterion, or is the verdict inconclusive?", "kind": "action", "id": "comparative-judgment-evidence-q03" } ] } ] } ] }, { "id": "trial-integrity-and-replication", "name": "Trial integrity and replication", "description": "Assesses whether recorded conversations and judgments support the claimed trial conditions.", "rationale": "Identity leakage, selective reporting and an unrecorded system configuration can undermine a claimed result.", "layers": [ { "id": "blinding-and-trial-record", "name": "Blinding and trial record", "description": "Checks identity concealment, assignment records and completeness of retained evidence.", "findings": [ { "id": "auditable-encounters", "name": "Auditable encounters", "description": "Link judgments to transcripts and assignment records while identifying exclusions, protocol deviations and possible identity disclosures.", "questions": [ { "text": "Can every included judgment be traced to an encounter, assignment and applicable instruction set?", "kind": "provenance", "id": "auditable-encounters-q01" }, { "text": "Which encounters were excluded or interrupted, and were those decisions governed by a declared rule?", "kind": "measurement", "id": "auditable-encounters-q02" }, { "text": "What evidence shows whether judges received unintended identity cues?", "kind": "measurement", "id": "auditable-encounters-q03" } ] } ] }, { "id": "system-and-population-stability", "name": "System and population stability", "description": "Determines which system configuration and judge population a result describes.", "findings": [ { "id": "replicable-test-conditions", "name": "Replicable test conditions", "description": "Record system version, prompting, memory, assistance and judge recruitment sufficiently to assess replication and limits of transfer.", "questions": [ { "text": "Which system version, instructions, memory state and external assistance produced the tested conversations?", "kind": "provenance", "id": "replicable-test-conditions-q01" }, { "text": "How were judges recruited, and what language skills, expertise or prior system exposure characterised them?", "kind": "measurement", "id": "replicable-test-conditions-q02" }, { "text": "Which conditions must a replication preserve, and which should it vary to test robustness?", "kind": "action", "id": "replicable-test-conditions-q03" } ] } ] } ] }, { "id": "inference-and-test-boundaries", "name": "Inference and test boundaries", "description": "Controls how trial outcomes are interpreted and how neighbouring evaluations are classified.", "rationale": "Conversational indistinguishability does not by itself settle every claim associated with machine intelligence.", "layers": [ { "id": "limits-of-passing", "name": "Limits of passing", "description": "Separates observed judge behaviour from broader theoretical and practical conclusions.", "findings": [ { "id": "licensed-conclusions", "name": "Licensed conclusions", "description": "Identify the narrow result established under the protocol and the additional premises required for claims about understanding, general competence or consciousness.", "questions": [ { "text": "What conclusion follows directly from the observed judgments under these particular conditions?", "kind": "boundary", "id": "licensed-conclusions-q01" }, { "text": "Which additional premises connect that outcome to a claim about intelligence or understanding, and who defends them?", "kind": "provenance", "id": "licensed-conclusions-q02" }, { "text": "Which complementary evaluation would address an important capability claim left unresolved by this trial?", "kind": "action", "id": "licensed-conclusions-q03" } ] } ] }, { "id": "variants-and-neighbours", "name": "Variants and neighbours", "description": "Distinguishes conversational test variants from extensions and evaluations with a different target.", "findings": [ { "id": "variant-membership", "name": "Variant membership", "description": "Classify an evaluation by its actual judgment task and channels, documenting departures from the selected core formulation.", "questions": [ { "text": "Does the evaluation retain human judgment of human-versus-machine conversational identity?", "kind": "boundary", "id": "variant-membership-q01" }, { "text": "If it adds embodiment, perception or another task, which attributed formulation makes it an extension of the Turing test?", "kind": "provenance", "id": "variant-membership-q02" }, { "text": "Should its outcome be compared with the core conversational test, reported separately or linked to a neighbouring model?", "kind": "action", "id": "variant-membership-q03" } ] } ] } ] }, { "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 describes the conversational machine-intelligence sense; there is no single universally accepted protocol or passing threshold.", "Behavioural and functionalist interpretations give successful performance evidential weight, while critics dispute whether it establishes understanding; neither interpretation should be presented as settled.", "The relationship between Turing's original imitation game and later test formulations is interpretively disputed; historical details and named variants should be checked against their original texts." ], "questions": [ { "id": "evidence-confidence-notes-q01", "text": "Which of these check these first hold for the sense of Turing test 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": [ "Text-only conversational Turing test", "Restricted-domain conversational Turing test", "Total Turing test, extending evaluation to perception and physical interaction" ], "questions": [ { "id": "evidence-kinds-q01", "text": "Which of these kinds and varieties hold for the sense of Turing test 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": [ "Framing philosophical debate about machine intelligence and behavioural evidence.", "Evaluating whether conversational systems can produce apparently human dialogue.", "Organising human-versus-machine judging competitions, including the historical Loebner Prize.", "Studying how judges attribute intelligence and humanness to conversational partners." ], "questions": [ { "id": "evidence-real-world-use-q01", "text": "Which of these real-world use hold for the sense of Turing test 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": "Machine conversations classified as human", "typical_range": "0-100; interpretation depends on the protocol and human comparison condition", "unit": "%" }, { "quantity": "Judge accuracy in distinguishing humans from machines", "typical_range": "0-100; chance performance depends on the judging task", "unit": "%" }, { "quantity": "Conversation duration", "typical_range": "Protocol-dependent; no universally required duration", "unit": "minutes" } ], "questions": [ { "id": "evidence-measurements-q01", "text": "Which of these typical measurements hold for the sense of Turing test 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": [ "Mistaking successful human imitation for proof of understanding, consciousness, or general intelligence.", "Results varying with judge expertise, language, conversation length, topic restrictions, and participant instructions.", "Evasion, deliberate mistakes, or fabricated personas exploiting judges' expectations without demonstrating broad competence.", "Reporting that a system passed without specifying the protocol, comparison group, threshold, or uncertainty.", "Treating failure to imitate human conversational habits as evidence that a system lacks useful intelligence." ], "questions": [ { "id": "evidence-failure-modes-and-hazards-q01", "text": "Which of these failure modes and hazards hold for the sense of Turing test 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": [ "Language, dialect, and cultural expectations affect judgments of conversational humanness and limit comparisons across populations." ], "questions": [ { "id": "evidence-regional-variation-q01", "text": "Which of these regional variation hold for the sense of Turing test 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": "Imitation game", "difference": "Turing's original presentation begins with a game involving concealed male and female participants; the later label Turing test usually denotes human-machine conversational discrimination." }, { "name": "CAPTCHA", "difference": "A CAPTCHA automatically screens users for access control, whereas a conventional Turing test uses human judges to assess machine imitation of human conversation." }, { "name": "Chinese room argument", "difference": "This is a philosophical argument about whether symbol manipulation entails understanding, rather than an empirical conversational test." }, { "name": "Artificial general intelligence", "difference": "General intelligence concerns competence across a broad range of tasks; conversational indistinguishability is a narrower behavioural criterion." } ], "questions": [ { "id": "evidence-neighbours-q01", "text": "Which of these neighbouring kinds and how to tell them apart hold for the sense of Turing test this model covers, and on what evidence?", "kind": "provenance" } ] } ] } ] } ] }, "openQuestions": [ "Which primary and scholarly sources best resolve differences between Turing's imitation-game formulations and later standard conversational interpretations?", "Which attributed positions treat passing as necessary, sufficient or merely evidential for intelligence, and where do their arguments diverge?", "Which implemented protocols justify their passing thresholds through human controls, statistical reasoning or historical convention?", "How strongly do judge expertise, disclosed machine prevalence, personas and conversation duration change outcomes across replicated studies?", "Which independently auditable trials support generalisation beyond a particular system configuration, judge population and interaction setting?" ], "statistics": { "bundles": 6, "layers": 11, "findings": 17, "questions": 35 } }, "draft": { "generator": "vr.draft.v3", "status": "draft-generated", "researched": false, "archetype": "abstract concept", "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 Turing test, record what state it is in, and decide what may be done with it.", "whatItIs": "Enable an AI agent to recognise a Turing-test proposal or trial, assess what its conversational evidence supports, and determine which conclusions or further evaluations are warranted.", "characteristics": { "substance": "activity", "origin": "conceptual", "agency": "inert" }, "whatYouCanDoWithIt": [ "observed and measured" ], "distinguishingFeatures": [ "Described in 69 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 Turing test, and on what evidence are they told apart?" ], "whatItIsMadeOf": "something that happens over time", "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": [ "observe it, measure it, record its state" ], "howItIsRecognised": [ "Nothing to see. What is recognised is an instance of it, and which instances count is exactly what is argued about." ], "relatedModels": [], "standing": "Described in 69 Wikipedia languages, which measures how widely it is written about rather than how important or how common it is.", "structure": { "bundles": [ { "id": "identity-and-classification", "name": "Identity, naming and classification", "description": "How an agent tells one Turing test from another, and a Turing test 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 Turing test, 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 Turing test, 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 Turing test 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 Turing test, 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 Turing test, 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 Turing test 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 Turing test 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 Turing test, 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 Turing test, 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 Turing test 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 Turing test from the things most often confused with it.", "questions": [ { "id": "distinguishing-features-q01", "text": "What identifies and describes what distinguishes a Turing test, 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 Turing test, 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 Turing test 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 Turing test 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 Turing test between them.", "questions": [ { "id": "stages-and-transitions-q01", "text": "What identifies and describes the lifecycle of a Turing test, 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 Turing test, 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 Turing test 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 Turing test, how often and by whom.", "findings": [ { "id": "observation-record", "name": "Observation record", "description": "How an observation of a Turing test 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 Turing test, 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 Turing test, 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 Turing test is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] } ] }, { "id": "process-and-outcome", "name": "Process, inputs and outcome", "description": "How a Turing test proceeds, what it needs and what it leaves behind.", "rationale": "An activity is known by its steps and its results, and both have to be recordable while it is still running.", "layers": [ { "id": "steps-and-sequence", "name": "Steps and sequence", "description": "The steps of a Turing test, their order and what may run in parallel.", "findings": [ { "id": "steps-and-preconditions", "name": "Steps, preconditions and completion", "description": "What has to be true before each step of a Turing test and what marks it done.", "questions": [ { "id": "steps-and-preconditions-q01", "text": "What identifies and describes a step of a Turing test, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "steps-and-preconditions-q02", "text": "Who or what asserted this about a step of a Turing test, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "steps-and-preconditions-q03", "text": "What may an agent decide or do once a step of a Turing test is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] }, { "id": "inputs-and-results", "name": "Inputs, resources and results", "description": "What a Turing test consumes and what it produces.", "findings": [ { "id": "inputs-and-outputs", "name": "Inputs, outputs and side effects", "description": "The resources a Turing test takes and the results it leaves, wanted or not.", "questions": [ { "id": "inputs-and-outputs-q01", "text": "What identifies and describes the inputs and results of a Turing test, and in what units or vocabulary?", "kind": "definition", "answer_data": [ "identifiers", "types and classes", "values with units", "explicit unknowns" ] }, { "id": "inputs-and-outputs-q02", "text": "Who or what asserted this about the inputs and results of a Turing test, by which method, and when was it true?", "kind": "provenance", "answer_data": [ "authority", "method", "evidence", "event time", "knowledge time" ] }, { "id": "inputs-and-outputs-q03", "text": "What may an agent decide or do once the inputs and results of a Turing test is known, and what must it refuse?", "kind": "action", "answer_data": [ "permitted actions", "preconditions", "refusals", "escalation" ] } ] } ] } ] }, { "id": "definitions-in-contest", "name": "Definitions and who holds them", "description": "What Turing test is taken to mean, and by whom.", "rationale": "When a field disagrees about a concept, the disagreement is the content. A model that picks one definition silently destroys the information.", "layers": [ { "id": "competing-definitions", "name": "Competing definitions", "description": "The main readings and the traditions behind them.", "findings": [ { "id": "definition-map", "name": "Definitions and their holders", "description": "Each definition with the school or body that holds it.", "questions": [ { "id": "definition-map-q01", "text": "Which definitions of Turing test are in use, and which tradition or body holds each?", "kind": "definition" }, { "id": "definition-map-q02", "text": "What turns on the difference between them in practice?", "kind": "boundary" } ] } ] }, { "id": "operationalisation", "name": "Operationalisation", "description": "How it is measured or applied when it has to be.", "findings": [ { "id": "operational-record", "name": "Measures and proxies", "description": "Instruments and indicators used to stand in for it.", "questions": [ { "id": "operational-record-q01", "text": "How is Turing test operationalised or measured in practice, and by what instrument?", "kind": "measurement" }, { "id": "operational-record-q02", "text": "What does that operationalisation leave out, and when does that matter?", "kind": "boundary" } ] } ] } ] }, { "id": "instances-and-use", "name": "Instances, use and consequence", "description": "What counts as an instance of Turing test and what follows from calling something that.", "rationale": "Applying a concept is an act with consequences, so a model must say what the label licenses and what it does not.", "layers": [ { "id": "instances", "name": "What counts as an instance", "description": "Clear cases, borderline cases and non-cases.", "findings": [ { "id": "instance-tests", "name": "Tests for an instance", "description": "What would settle whether something falls under it.", "questions": [ { "id": "instance-tests-q01", "text": "What would settle whether something is an instance of Turing test?", "kind": "boundary" }, { "id": "instance-tests-q02", "text": "Which borderline cases are argued about, and on what grounds?", "kind": "definition" } ] } ] }, { "id": "consequence", "name": "Consequence of application", "description": "Rights, duties or decisions that follow from the label.", "findings": [ { "id": "consequence-record", "name": "What the label licenses", "description": "What an agent may do once something is classified this way.", "questions": [ { "id": "consequence-record-q01", "text": "What follows practically once something is treated as Turing test?", "kind": "action" }, { "id": "consequence-record-q02", "text": "What must an agent not infer from the label alone?", "kind": "action" } ] } ] } ] }, { "id": "provenance-and-evidence", "name": "Provenance, evidence and time", "description": "Where every claim about a Turing test 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 Turing test and how confident it is.", "questions": [ { "id": "claim-provenance-q01", "text": "What identifies and describes a claim about a Turing test, 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 Turing test, 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 Turing test 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 Turing test is retired without being erased.", "questions": [ { "id": "validity-and-supersession-q01", "text": "What identifies and describes the validity of a claim about a Turing test, 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 Turing test, 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 Turing test 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 } } } }