{ "model": { "rank": 6629, "code": "thing-q653347", "model_id": "vr.tr.hate-speech", "name": "hate speech", "purpose": "Enable an AI agent to recognise possible hate speech, record the evidence and interpretive framework behind that assessment, evaluate contextual harm, and select proportionate responses.", "family": "Thing Registry", "category": "Activities and processes", "status": "research-draft", "kind": "thing", "plane": "ACT", "domain": "ACT.ACT", "industry": "", "version": "", "url": "/models/thing/q653347/", "tier": 2, "score": 59, "payload": { "layer": "wikidata", "aliases": [ "Hate speech in Japan", "hate speech in the United States", "anti-LGBTQ rhetoric", "online hate speech", "incitement to genocide" ], "aliasCount": 5, "merged": 5, "knownIn": 59, "facets": null, "markers": [], "lexicalClass": "", "senseRank": null, "alsoRegisteredAs": null, "source": { "dataset": "wikidata", "item": "Q653347", "url": "https://www.wikidata.org/wiki/Q653347", "license": "CC0 1.0" } }, "research": { "vercy": "1.0-draft", "publication": { "status": "research-draft", "adjudicationStatus": "unreviewed", "publishableCanonical": false, "generatedAt": "2026-09-09T23:10:13Z", "providers": [ "Codex" ], "breadth": "recalled by Codex without web access - no source was read", "missingProviders": [], "pass": 2, "cost": { "grok": { "seconds": 25.3, "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: 01a0886e-b135-7df1-9e8e-aa9d31c0f8b2\n--------\nuser\nDescribe what is already known about one registered thing. Answer as JSON only, no prose around it.\n\nThing: hate speech\nSense to describe: (none recorded)\nDomain code: ACT.ACT\nAlso known as: (none)\n\n\nContext for this batch of 1001 things:\n# Batch 007: 1001 reg", "usd": 0, "recall": true }, "codex": { "seconds": 63.1, "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: 01a0886e-b143-78d2-8c80-cfc664285cb8\n--------\nuser\nYou are drafting a Vercy meta-model for one registered thing. Answer as JSON only, no prose around it.\n\nThing: hate speech\nRegistry id: vr.tr.hate-speech\nPlane / domain: ACT / ACT.ACT\nRegistry definition: (none recorded)\nNames folded into this entry: (none)\n\n\n" } } }, "metaModel": { "id": "THING-Q653347", "registryId": "vr.tr.hate-speech", "name": "hate speech", "version": "0.1.0-research.1", "entryKind": "thing", "family": "Thing Registry", "domain": [ "ACT.ACT" ], "status": "research-draft" }, "canonicalUrl": "https://ver.cy/models/thing/q653347/", "model": { "registry_id": "vr.tr.hate-speech", "name": "hate speech", "purpose": "Enable an AI agent to recognise possible hate speech, record the evidence and interpretive framework behind that assessment, evaluate contextual harm, and select proportionate responses.", "definition": "Hate speech is a contested category of expression that attacks, demeans or promotes hostility, discrimination or violence against people on grounds of group identity, with definitions differing over covered characteristics, context and thresholds of harm.", "scope_statement": "This model owns identity-directed communicative acts assessed as possible hate speech, including contested definitions, contextual interpretation, harm assessment, and response decisions; it does not assume that a descriptive classification establishes illegality.", "in_scope": [ "Communicative acts that attack, demean, exclude, threaten, or encourage hostility toward people through attributed group identity", "Competing definitions and their treatment of targets, expression, intent, context, and harm", "Explicit, coded, visual, audiovisual, and multimodal expressions", "Distinguishing endorsement from reporting, quotation, counterspeech, satire, and reclamation", "Evidence, uncertainty, and proportionate handling of suspected instances" ], "out_of_scope": [ "Prejudice or hatred without an identifiable communicative act", "Harassment lacking the identity connection required by the applicable definition", "Discrimination in employment, housing, or services as conduct beyond the expression itself", "Violent acts and operational threat management beyond the speech assessment", "General misinformation assessment and platform governance as whole systems" ], "distinguishing_features": [ "Identify whether hostility targets people through actual or attributed group identity; disagreement with an idea alone does not establish this connection.", "Test whether the expression performs an attack, degradation, exclusion, threat, or encouragement of hostility under a named definition, rather than treating offensiveness as sufficient.", "Determine whether the speaker endorses the hostile message or quotes, rejects, documents, satirises, or reclaims it.", "Resolve coded meanings through contextual evidence rather than classifying an isolated word or symbol automatically.", "Assess descriptive classification, platform-rule violation, and legal restriction separately because their criteria may differ." ], "characteristics": [ { "name": "Assessment framework", "kind": "relation", "unit_or_values": "Named definition, research codebook, community standard, or legal instrument with issuer, version, and applicability", "why_it_matters": "Makes the criteria and limits of a classification explicit." }, { "name": "Target and identity connection", "kind": "relation", "unit_or_values": "Targeted people or group; attributed identity; explicit, contextual, disputed, or unresolved connection", "why_it_matters": "Separates identity-directed hostility from neighbouring forms of abuse or criticism." }, { "name": "Communicative function", "kind": "category", "unit_or_values": "Derogation, dehumanisation, collective blame, exclusion, threat, encouragement of hostility, other, or unresolved; multiple values permitted", "why_it_matters": "Records what the expression does rather than relying on a keyword match." }, { "name": "Speaker stance toward the hostile content", "kind": "state", "unit_or_values": "Endorsement, rejection, reporting, quotation with unclear stance, satire, reclamation, mixed, or unresolved", "why_it_matters": "Helps prevent documentation and resistance from being classified as endorsement." }, { "name": "Expression and coding", "kind": "category", "unit_or_values": "Text, speech, image, gesture, audio, video, or mixed; explicit, coded, or ambiguous", "why_it_matters": "Identifies which linguistic, cultural, and multimodal evidence interpretation requires." }, { "name": "Observed dissemination", "kind": "measurement", "unit_or_values": "Views, recipients, shares, or repetitions within a stated observation period; unknown where unavailable", "why_it_matters": "Supports assessment of exposure while keeping measured reach distinct from assumed influence." }, { "name": "Contextual harm assessment", "kind": "state", "unit_or_values": "Evidence-supported description of potential harm, affected people, urgency, and uncertainty", "why_it_matters": "Supports response decisions without treating offensive language as a complete measure of risk." }, { "name": "Classification outcome", "kind": "state", "unit_or_values": "Meets, does not meet, or unresolved under each named framework, with reasons and evidence gaps", "why_it_matters": "Preserves disagreement and avoids presenting one assessment as universally authoritative." } ], "affordances": [ "Assess an expression against a named definition and explain which criteria are supported or unresolved.", "Compare outcomes across definitions without collapsing their differences.", "Request missing conversational, linguistic, cultural, or dissemination context.", "Preserve necessary evidence with controlled access and minimal repetition of harmful content.", "Recommend proportionate responses within the agent's authority, including contextualisation, review, or escalation.", "Reassess a decision when an appeal, corrected translation, or new contextual evidence arrives." ] }, "sources": [], "structure": { "bundles": [ { "id": "definitions-and-boundaries", "name": "Definitions and boundaries", "description": "Records what counts as hate speech under particular frameworks and where those frameworks disagree.", "rationale": "The registry has no definition, and a useful model must expose competing criteria rather than silently select one.", "layers": [ { "id": "framework-criteria", "name": "Framework criteria", "description": "Identifies the authority, scope, and decision criteria of each definition.", "findings": [ { "id": "definition-dependent-classification", "name": "Definition-dependent classification", "description": "Record each assessment against an identified framework, including which identities and communicative functions it covers.", "questions": [ { "text": "Whose definition is being applied, and what target, expression, intent, or harm criteria does it require?", "kind": "definition", "id": "definition-dependent-classification-q01" }, { "text": "Which original document and version establish those criteria?", "kind": "provenance", "id": "definition-dependent-classification-q02" } ] } ] }, { "id": "neighbouring-expression", "name": "Neighbouring expression", "description": "Tests boundaries with insult, criticism, harassment, threats, and discriminatory advocacy.", "findings": [ { "id": "identity-and-attack-boundary", "name": "Identity and attack boundary", "description": "Require an explained connection between the target, attributed identity, and hostile communicative function.", "questions": [ { "text": "What evidence connects the attack to people's identity rather than solely to their actions, ideas, or institutional role?", "kind": "boundary", "id": "identity-and-attack-boundary-q01" }, { "text": "Would the expression meet the selected definition if its offensive vocabulary were replaced by neutral wording?", "kind": "boundary", "id": "identity-and-attack-boundary-q02" } ] } ] } ] }, { "id": "targets-and-hostile-functions", "name": "Targets and hostile functions", "description": "Represents who is targeted and what the communication seeks or appears to do to them.", "rationale": "Hate-speech assessment needs more precision than a label of negative sentiment.", "layers": [ { "id": "target-identification", "name": "Target identification", "description": "Identifies individual, collective, indirect, and intersecting targets.", "findings": [ { "id": "attributed-group-membership", "name": "Attributed group membership", "description": "Record the identity attributed by the expression without asserting that the target actually holds it.", "questions": [ { "text": "Who is targeted, and which actual or attributed group membership makes them the target?", "kind": "definition", "id": "attributed-group-membership-q01" }, { "text": "Is the target named directly, inferred through a proxy, or unresolved, and what supports that interpretation?", "kind": "provenance", "id": "attributed-group-membership-q02" } ] } ] }, { "id": "hostile-communicative-function", "name": "Hostile communicative function", "description": "Distinguishes forms of identity-directed hostility and their combinations.", "findings": [ { "id": "attack-and-exclusion-mechanisms", "name": "Attack and exclusion mechanisms", "description": "Describe the expression's function, including degradation, dehumanisation, collective blame, exclusion, threats, or encouragement of hostile action.", "questions": [ { "text": "Which hostile function is evidenced by the expression, and which specific content supports it?", "kind": "definition", "id": "attack-and-exclusion-mechanisms-q01" }, { "text": "Does the message express contempt, advocate unequal treatment, threaten harm, or encourage others to act, and where is the distinction uncertain?", "kind": "boundary", "id": "attack-and-exclusion-mechanisms-q02" } ] } ] } ] }, { "id": "meaning-and-context", "name": "Meaning and context", "description": "Determines how the expression functions within its conversation, language, medium, and audience.", "rationale": "Identical words or symbols can support different assessments depending on stance and context.", "layers": [ { "id": "quotation-and-stance", "name": "Quotation and stance", "description": "Separates hostile content appearing in a message from the communicator's position toward it.", "findings": [ { "id": "endorsement-versus-reference", "name": "Endorsement versus reference", "description": "Record evidence of endorsement, rejection, documentation, satire, or reclamation without treating a claimed purpose as conclusive.", "questions": [ { "text": "Does the surrounding communication endorse the hostile content or use it for reporting, counterspeech, satire, or reclamation?", "kind": "boundary", "id": "endorsement-versus-reference-q01" }, { "text": "Which conversational turns, captions, or other contextual evidence establish the speaker's stance?", "kind": "provenance", "id": "endorsement-versus-reference-q02" } ] } ] }, { "id": "coded-and-multimodal-meaning", "name": "Coded and multimodal meaning", "description": "Examines indirect references, local usage, translation, and interactions between modalities.", "findings": [ { "id": "context-supported-decoding", "name": "Context-supported decoding", "description": "Treat proposed coded meanings as interpretations requiring evidence and consideration of plausible alternatives.", "questions": [ { "text": "What evidence supports the alleged hostile meaning of a euphemism, symbol, meme, or combination of text and imagery in this setting?", "kind": "provenance", "id": "context-supported-decoding-q01" }, { "text": "Could dialect, translation, local usage, or missing audiovisual context materially change the assessment?", "kind": "boundary", "id": "context-supported-decoding-q02" } ] } ] } ] }, { "id": "exposure-and-harm", "name": "Exposure and harm", "description": "Assesses circulation, audience context, and plausible pathways from expression to harm.", "rationale": "Classification alone does not establish the severity, urgency, or consequences of an instance.", "layers": [ { "id": "circulation-and-audience", "name": "Circulation and audience", "description": "Records observed dissemination and relevant speaker-audience relationships.", "findings": [ { "id": "exposure-without-assumed-impact", "name": "Exposure without assumed impact", "description": "Separate measured circulation from estimates of influence or audience response.", "questions": [ { "text": "What reach, repetition, or amplification was observed, over what period, and through which measurement source?", "kind": "measurement", "id": "exposure-without-assumed-impact-q01" }, { "text": "What evidence shows the speaker's authority or influence with this audience, rather than merely their follower count?", "kind": "provenance", "id": "exposure-without-assumed-impact-q02" } ] } ] }, { "id": "harm-pathways-and-urgency", "name": "Harm pathways and urgency", "description": "Examines potential intimidation, exclusion, discrimination, and violence in the specific setting.", "findings": [ { "id": "evidence-based-harm-assessment", "name": "Evidence-based harm assessment", "description": "Record plausible harm pathways, observed effects, and uncertainty separately; identify concrete signals requiring urgent review.", "questions": [ { "text": "Which harms are observed, which are anticipated, and what evidence connects them to this expression?", "kind": "measurement", "id": "evidence-based-harm-assessment-q01" }, { "text": "Do specific targets, calls to act, timing, or surrounding events warrant urgent threat review under the applicable procedure?", "kind": "action", "id": "evidence-based-harm-assessment-q02" } ] } ] } ] }, { "id": "decisions-and-contestability", "name": "Decisions and contestability", "description": "Connects supported assessments to authorised responses and revisable decisions.", "rationale": "An agent must distinguish interpreting speech from having authority to restrict it and must preserve routes for correction.", "layers": [ { "id": "response-selection", "name": "Response selection", "description": "Evaluates responses against the applicable rules, evidence, urgency, and potential adverse effects.", "findings": [ { "id": "proportionate-authorised-response", "name": "Proportionate authorised response", "description": "Record the basis for contextualisation, review, distribution limits, removal, or escalation as distinct decisions.", "questions": [ { "text": "What action is authorised by the applicable rule and supported by the evidence and assessed urgency?", "kind": "action", "id": "proportionate-authorised-response-q01" }, { "text": "Could the proposed response suppress reporting, counterspeech, or a targeted community's own expression, and how should that affect the decision?", "kind": "action", "id": "proportionate-authorised-response-q02" } ] } ] }, { "id": "review-and-evidence", "name": "Review and evidence", "description": "Preserves the grounds for a decision and enables correction without unnecessary redistribution.", "findings": [ { "id": "revisable-assessment-record", "name": "Revisable assessment record", "description": "Retain necessary evidence, framework versions, reasons, and unresolved disagreements with appropriate access controls.", "questions": [ { "text": "What minimum evidence and context must be retained so another reviewer can reconstruct the assessment?", "kind": "provenance", "id": "revisable-assessment-record-q01" }, { "text": "What new evidence, appeal, or framework change would require reconsideration, and who can revise the outcome?", "kind": "action", "id": "revisable-assessment-record-q02" } ] } ] } ] }, { "id": "evidence-and-external-alignment", "name": "Evidence and external alignment", "description": "What the world already says about this thing, gathered so the model can be checked against it.", "rationale": "A model that cannot be lined up against existing standards, identifiers and practice cannot be adopted by anyone who already uses them.", "layers": [ { "id": "reported-evidence", "name": "Reported evidence", "description": "Findings from the breadth pass, kept separate from the structural claims.", "findings": [ { "id": "evidence-confidence-notes", "name": "Check these first", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ "This is a recall-based description; no sources were consulted.", "There is no single universally accepted definition; a researcher should specify whether the intended category is legal, institutional or analytical.", "The listed kinds overlap, and current jurisdiction-specific law and platform policies require verification before application." ], "questions": [ { "id": "evidence-confidence-notes-q01", "text": "Which of these check these first hold for the sense of hate speech 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": [ "Identity-based insults and derogation", "Dehumanizing or demonizing expression", "Advocacy of exclusion or discrimination", "Incitement to hatred or violence", "Identity-based threats", "Coded or implicit expressions of group hatred" ], "questions": [ { "id": "evidence-kinds-q01", "text": "Which of these kinds and varieties hold for the sense of hate speech this model covers, and on what evidence?", "kind": "provenance" } ] }, { "id": "evidence-standards-and-regulation", "name": "Standards and regulation", "description": "Recalled without web access and unsourced; every item is a lead to verify.", "evidence": [ "United Nations: International Covenant on Civil and Political Rights, Article 19 protects freedom of expression subject to specified restrictions; Article 20(2) requires prohibition by law of advocacy of national, racial or religious hatred constituting incitement to discrimination, hostility or violence.", "United Nations: International Convention on the Elimination of All Forms of Racial Discrimination, Article 4 addresses racist propaganda, incitement and organizations.", "United Nations Office of the High Commissioner for Human Rights: Rabat Plan of Action provides a six-part threshold test for assessing incitement, covering context, speaker, intent, content and form, extent, and likelihood including imminence.", "Council of Europe Committee of Ministers: Recommendation CM/Rec(2022)16 on combating hate speech distinguishes levels of severity and corresponding responses.", "Council of the European Union: Framework Decision 2008/913/JHA addresses certain forms and expressions of racism and xenophobia through criminal law." ], "questions": [ { "id": "evidence-standards-and-regulation-q01", "text": "Which of these standards and regulation hold for the sense of hate speech 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": [ "A category in platform content policies and moderation decisions.", "A concept used in evaluating potentially unlawful incitement and discriminatory expression.", "A research category for studying prejudice, intergroup hostility and online abuse.", "A monitoring category in atrocity prevention and assessments of threats to targeted communities.", "A focus of education, counterspeech and support for people targeted by identity-based abuse." ], "questions": [ { "id": "evidence-real-world-use-q01", "text": "Which of these real-world use hold for the sense of hate speech 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": "Proportion of sampled content classified as hate speech under a specified definition", "typical_range": "No universal typical range; depends on sampling, platform, language and classification rules", "unit": "Percent of sampled items" }, { "quantity": "Precision and recall of a hate-speech classifier against an annotated reference set", "typical_range": "No universal typical range; depends on the dataset and annotation standard", "unit": "Dimensionless proportion" } ], "questions": [ { "id": "evidence-measurements-q01", "text": "Which of these typical measurements hold for the sense of hate speech 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": [ "Expression can intimidate targeted people, normalize discrimination and contribute to conditions supporting violence; effects depend on context.", "Overbroad definitions can suppress legitimate criticism, dissent, satire or discussion of religion and politics.", "Quotation, counterspeech and reclaimed slurs can be misclassified when context is ignored.", "Automated systems can miss coded hostility and disproportionately flag language used by marginalized communities.", "Inconsistent definitions, sampling and annotation can make prevalence estimates misleading or incomparable." ], "questions": [ { "id": "evidence-failure-modes-and-hazards-q01", "text": "Which of these failure modes and hazards hold for the sense of hate speech 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": [ "United States constitutional doctrine generally does not recognize hate speech as a standalone exception to free-speech protection; particular expression may fall within categories such as true threats or incitement.", "European jurisdictions commonly restrict some racist or other identity-based expression, but protected characteristics, thresholds and penalties vary.", "Across jurisdictions, treatment of religious hatred, criticism of religion and blasphemy differs; these categories should not be treated as interchangeable." ], "questions": [ { "id": "evidence-regional-variation-q01", "text": "Which of these regional variation hold for the sense of hate speech 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": "Offensive speech", "difference": "Offensiveness alone does not establish an identity-based attack or satisfy a particular hate-speech definition." }, { "name": "Incitement", "difference": "Incitement concerns prompting others toward prohibited conduct or outcomes; it need not involve group identity, and many definitions of hate speech include expression below an incitement threshold." }, { "name": "Harassment", "difference": "Harassment concerns abusive or intimidating conduct toward people and need not be based on group identity." }, { "name": "Hate crime", "difference": "A hate crime requires a criminal offense with the relevant bias element; expression classified as hate speech is not necessarily criminal." }, { "name": "Discrimination", "difference": "Discrimination concerns unequal treatment or disadvantage on specified grounds; hate speech concerns expression, though an act can involve both." }, { "name": "Criticism of beliefs or institutions", "difference": "Criticizing ideas, practices or institutions does not by itself constitute an attack on people because of their identity; wording and context determine possible overlap." } ], "questions": [ { "id": "evidence-neighbours-q01", "text": "Which of these neighbouring kinds and how to tell them apart hold for the sense of hate speech this model covers, and on what evidence?", "kind": "provenance" } ] } ] } ] } ] }, "openQuestions": [ "Which reference definitions should anchor this registry entry, and how do their identity, intent, and harm criteria differ?", "How should the model represent disagreement over attacks on dominant groups, institutions, religions, and ideologies without conflating criticism with attacks on people?", "What evidence is sufficient to classify emerging coded expressions across languages and communities?", "Which methods can assess cumulative harm from repeated identity-directed expression without attributing collective effects to an isolated message without support?", "How should practical response thresholds balance uncertainty, urgency, and the risk of suppressing documentation, counterspeech, or reclaimed language?" ], "statistics": { "bundles": 6, "layers": 11, "findings": 18, "questions": 28 } }, "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 hate speech, record what state it is in, and decide what may be done with it.", "whatItIs": "Enable an AI agent to recognise possible hate speech, record the evidence and interpretive framework behind that assessment, evaluate contextual harm, and select proportionate responses.", "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: Hate speech in Japan, hate speech in the United States, anti-LGBTQ rhetoric, online hate speech, incitement to genocide.", "5 finer distinctions are held as aliases rather than separate entries, because telling them apart needs a task that asks for it.", "Described in 59 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 hate speech, 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": [ "Hate speech in Japan", "hate speech in the United States", "anti-LGBTQ rhetoric", "online hate speech", "incitement to genocide" ] } ], "standing": "Described in 59 Wikipedia languages, which measures how widely it is written about rather than how important or how common it is. 5 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 hate speech from another, and a hate speech 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 hate speech, 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 hate speech, 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 hate speech 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 hate speech, 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 hate speech, 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 hate speech 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 hate speech 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 hate speech, 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 hate speech, 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 hate speech 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 hate speech from the things most often confused with it.", "questions": [ { "id": "distinguishing-features-q01", "text": "What identifies and describes what distinguishes a hate speech, 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 hate speech, 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 hate speech 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 hate speech 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 hate speech between them.", "questions": [ { "id": "stages-and-transitions-q01", "text": "What identifies and describes the lifecycle of a hate speech, 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 hate speech, 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 hate speech 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 hate speech, how often and by whom.", "findings": [ { "id": "observation-record", "name": "Observation record", "description": "How an observation of a hate speech 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 hate speech, 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 hate speech, 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 hate speech 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 hate speech 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 hate speech, 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 hate speech and what marks it done.", "questions": [ { "id": "steps-and-preconditions-q01", "text": "What identifies and describes a step of a hate speech, 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 hate speech, 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 hate speech 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 hate speech consumes and what it produces.", "findings": [ { "id": "inputs-and-outputs", "name": "Inputs, outputs and side effects", "description": "The resources a hate speech 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 hate speech, 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 hate speech, 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 hate speech 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 hate speech 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 hate speech 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 hate speech 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 hate speech 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 hate speech?", "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 hate speech?", "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 hate speech 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 hate speech and how confident it is.", "questions": [ { "id": "claim-provenance-q01", "text": "What identifies and describes a claim about a hate speech, 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 hate speech, 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 hate speech 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 hate speech is retired without being erased.", "questions": [ { "id": "validity-and-supersession-q01", "text": "What identifies and describes the validity of a claim about a hate speech, 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 hate speech, 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 hate speech 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 } } } }