{ "model": { "rank": 5411, "code": "thing-q172491", "model_id": "vr.tr.data-mining", "name": "data mining", "purpose": "Let an agent explain data mining, relay methods, process models, applications, privacy risks and regulation from computer science, statistics and data protection sources with debates attributed, describe the named methods and flag attack aliases as related risks without enabling attacks, and distinguish data mining from data collection, machine learning in general, statistics, text and data mining copyright exceptions and data dredging.", "family": "Thing Registry", "category": "Activities and processes", "status": "research-draft", "kind": "thing", "plane": "ACT", "domain": "ACT.ACT", "industry": "", "version": "", "url": "/models/thing/q172491/", "tier": 2, "score": 67, "payload": { "layer": "wikidata", "aliases": [ "inference attack", "unsupervised clustering", "Membership inference attack", "hierarchical clustering", "Brown clustering", "argument mining", "extracting structured information", "knowledge extraction", "process mining", "Cross-industry standard process for data mining", "structure mining", "association rule learning", "Cyborg Data Mining", "bibliomining", "cluster analysis", "affinity analysis", "relational data mining", "web mining", "decision mining", "single-cell clustering", "supervised clustering", "parameter free clustering", "Biclustering", "space-time clustering" ], "aliasCount": 24, "merged": 24, "knownIn": 67, "facets": null, "markers": [], "lexicalClass": "", "senseRank": null, "alsoRegisteredAs": null, "source": { "dataset": "wikidata", "item": "Q172491", "url": "https://www.wikidata.org/wiki/Q172491", "license": "CC0 1.0" } }, "research": { "vercy": "1.0-draft", "publication": { "status": "research-draft", "adjudicationStatus": "unreviewed", "publishableCanonical": false, "generatedAt": "2026-09-13T23:53:45Z", "providers": [ "Claude" ], "breadth": "written by Claude from model knowledge without web access - no source was read, every claim is a lead to verify", "pass": 2, "wave": 4, "engine": "claude" }, "metaModel": { "id": "THING-Q172491", "registryId": "vr.tr.data-mining", "name": "data mining", "version": "0.2.0-wave.4", "entryKind": "thing", "family": "Thing Registry", "domain": [ "ACT.ACT" ], "status": "research-draft" }, "canonicalUrl": "https://ver.cy/models/thing/q172491/", "model": { "registry_id": "vr.tr.data-mining", "name": "data mining", "purpose": "Let an agent explain data mining, relay methods, process models, applications, privacy risks and regulation from computer science, statistics and data protection sources with debates attributed, describe the named methods and flag attack aliases as related risks without enabling attacks, and distinguish data mining from data collection, machine learning in general, statistics, text and data mining copyright exceptions and data dredging.", "definition": "The process of discovering patterns, correlations and anomalies in large datasets using methods from statistics, machine learning and databases, including classification, association rule mining, clustering methods the registry aliases name such as unsupervised, hierarchical and Brown clustering, anomaly detection, and text mining tasks such as argument mining; it is part of knowledge discovery in databases and is used in business, science, healthcare and security. The aliases inference attack and membership inference attack name privacy attacks that deduce sensitive information from data or trained models, a related risk area. Data mining of personal data is regulated by data protection laws such as the GDPR, and ethics debates are attributed.", "what_it_is_for": "Discovering patterns in data.", "affordances": [ "explain methods and process", "relay applications", "describe named methods and privacy risks", "relay regulation" ], "distinguishing_features": [ "Large datasets", "Pattern discovery", "Algorithmic methods", "Privacy implications" ], "appearance": "Not a physical object; seen in analyses, models, dashboards and reports.", "visual_identification": [ "Pattern discovery in large datasets", "Inference attack, unsupervised clustering, membership inference attack, hierarchical clustering, Brown clustering, argument mining", "Data collection gathers data; machine learning builds models broadly; statistics tests hypotheses; TDM exceptions are legal rules; data dredging finds spurious results" ], "physical_properties": [ { "quantity": "KDD process described", "typical_range": "1996", "unit": "year", "note": "Fayyad and colleagues" }, { "quantity": "CRISP-DM", "typical_range": "1999-2000", "unit": "note", "note": "process model" }, { "quantity": "Brown clustering", "typical_range": "1992", "unit": "year", "note": "word clustering" } ], "families_and_kinds": [ "classification and prediction", "clustering", "association rule mining", "anomaly detection", "text and argument mining" ], "related_models": [ { "relation": "is a kind of", "target": "text and data mining", "why": "in registry terms" }, { "relation": "uses", "target": "cluster analysis", "why": "" }, { "relation": "is threatened by", "target": "membership inference attack", "why": "privacy risk" }, { "relation": "is contrasted with", "target": "data dredging", "why": "" } ], "identifiers": [], "standards_and_regulation": [ "GDPR and data protection laws", "EU AI Act", "Text and data mining exceptions in copyright law" ], "failure_modes_and_hazards": [ "Privacy violations", "Spurious patterns from data dredging", "Enabling re-identification attacks" ], "in_scope": [], "out_of_scope": [], "characteristics": [] }, "sources": [], "structure": { "bundles": [ { "id": "understand", "name": "Understand", "description": "What data mining is.", "rationale": "Attribution.", "layers": [ { "id": "definition", "name": "Definition", "description": "Definition.", "findings": [ { "id": "definition-finding", "name": "Definition", "description": "Definition.", "questions": [ { "text": "What is data mining, and how does it differ from data collection, machine learning, statistics, TDM exceptions and data dredging?", "kind": "definition" }, { "text": "Is the question about methods, a privacy concern, which data protection authorities handle, or legal permissions?", "kind": "boundary" } ] } ] }, { "id": "methods", "name": "Methods", "description": "Named methods.", "findings": [ { "id": "methods-finding", "name": "Methods", "description": "Methods.", "questions": [ { "text": "What are unsupervised, hierarchical and Brown clustering and argument mining, and what are inference attacks in general terms?", "kind": "definition" }, { "text": "Which entry fits the specific method?", "kind": "action" } ] } ] } ] }, { "id": "methods", "name": "Methods", "description": "Process.", "rationale": "Sources.", "layers": [ { "id": "kdd", "name": "KDD", "description": "Knowledge discovery.", "findings": [ { "id": "kdd-finding", "name": "KDD", "description": "KDD.", "questions": [ { "text": "How do KDD and CRISP-DM structure data mining projects?", "kind": "provenance" }, { "text": "Which references are standard?", "kind": "provenance" } ] } ] }, { "id": "clustering", "name": "Clustering", "description": "Clustering.", "findings": [ { "id": "clustering-finding", "name": "Clustering", "description": "Clustering.", "questions": [ { "text": "How do hierarchical and other clustering methods group data?", "kind": "provenance" }, { "text": "Which sources are cited?", "kind": "provenance" } ] } ] } ] }, { "id": "privacy", "name": "Privacy", "description": "Privacy and law.", "rationale": "Regulation.", "layers": [ { "id": "gdpr", "name": "GDPR", "description": "Data protection.", "findings": [ { "id": "gdpr-finding", "name": "GDPR", "description": "GDPR.", "questions": [ { "text": "How do data protection laws limit mining personal data?", "kind": "provenance" }, { "text": "Which entry fits General Data Protection Regulation?", "kind": "action" } ] } ] }, { "id": "attacks", "name": "Attacks", "description": "Privacy attacks.", "findings": [ { "id": "attacks-finding", "name": "Attacks", "description": "Attacks.", "questions": [ { "text": "What are membership inference risks and defences such as differential privacy, in general terms?", "kind": "provenance" }, { "text": "Which entry fits differential privacy?", "kind": "action" } ] } ] } ] }, { "id": "context", "name": "Context", "description": "Ethics.", "rationale": "Attribution.", "layers": [ { "id": "ethics", "name": "Ethics", "description": "Ethics debates.", "findings": [ { "id": "ethics-finding", "name": "Ethics", "description": "Ethics.", "questions": [ { "text": "What debates exist about data mining in marketing, policing and health, with positions attributed?", "kind": "provenance" }, { "text": "Is the presentation neutral and attributed?", "kind": "boundary" } ] } ] }, { "id": "dredging", "name": "Data dredging", "description": "Spurious patterns.", "findings": [ { "id": "dredging-finding", "name": "Data dredging", "description": "Data dredging.", "questions": [ { "text": "How can mining find false patterns, and how do statisticians guard against it?", "kind": "provenance" }, { "text": "Which entry fits data dredging?", "kind": "action" } ] } ] } ] } ] }, "openQuestions": [ "The registry aliases inference attack and membership inference attack should be moved to privacy attack entries", "Should argument mining be a separate entry?", "How should data protection guidance be linked?" ], "statistics": { "bundles": 4, "layers": 8, "findings": 8, "questions": 16 } }, "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 data mining, record what state it is in, and decide what may be done with it.", "whatItIs": "Let an agent explain data mining, relay methods, process models, applications, privacy risks and regulation from computer science, statistics and data protection sources with debates attributed, describe the named methods and flag attack aliases as related risks without enabling attacks, and distinguish data mining from data collection, machine learning in general, statistics, text and data mining copyright exceptions and data dredging.", "characteristics": { "substance": "activity", "origin": "conceptual", "agency": "inert" }, "whatYouCanDoWithIt": [ "observed and measured" ], "distinguishingFeatures": [ "Names folded into this entry, which a task may need to split apart again: inference attack, unsupervised clustering, Membership inference attack, hierarchical clustering, Brown clustering, argument mining, extracting structured information, knowledge extraction, process mining, Cross-industry standard process for data mining, structure mining, association rule learning.", "24 finer distinctions are held as aliases rather than separate entries, because telling them apart needs a task that asks for it.", "Described in 67 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 data mining, 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": [ { "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": [ "inference attack", "unsupervised clustering", "Membership inference attack", "hierarchical clustering", "Brown clustering", "argument mining", "extracting structured information", "knowledge extraction", "process mining", "Cross-industry standard process for data mining", "structure mining", "association rule learning" ] } ], "standing": "Described in 67 Wikipedia languages, which measures how widely it is written about rather than how important or how common it is. 24 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 data mining from another, and a data mining 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 data mining, 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 data mining, 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 data mining 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 data mining, 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 data mining, 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 data mining 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 data mining 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 data mining, 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 data mining, 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 data mining 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 data mining from the things most often confused with it.", "questions": [ { "id": "distinguishing-features-q01", "text": "What identifies and describes what distinguishes a data mining, 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 data mining, 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 data mining 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 data mining 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 data mining between them.", "questions": [ { "id": "stages-and-transitions-q01", "text": "What identifies and describes the lifecycle of a data mining, 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 data mining, 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 data mining 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 data mining, how often and by whom.", "findings": [ { "id": "observation-record", "name": "Observation record", "description": "How an observation of a data mining 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 data mining, 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 data mining, 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 data mining 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 data mining 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 data mining, 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 data mining and what marks it done.", "questions": [ { "id": "steps-and-preconditions-q01", "text": "What identifies and describes a step of a data mining, 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 data mining, 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 data mining 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 data mining consumes and what it produces.", "findings": [ { "id": "inputs-and-outputs", "name": "Inputs, outputs and side effects", "description": "The resources a data mining 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 data mining, 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 data mining, 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 data mining 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 data mining 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 data mining 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 data mining 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 data mining 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 data mining?", "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 data mining?", "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 data mining 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 data mining and how confident it is.", "questions": [ { "id": "claim-provenance-q01", "text": "What identifies and describes a claim about a data mining, 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 data mining, 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 data mining 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 data mining is retired without being erased.", "questions": [ { "id": "validity-and-supersession-q01", "text": "What identifies and describes the validity of a claim about a data mining, 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 data mining, 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 data mining 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 } } } }