Event details

Retrieve one World V2.0 event by identifier: a lite record by default, the complete record with view=full.

GET/api/v2.0/events/{date}/{event_id}

Authorizations

Bearer

Authorizationstringrequiredheader

Required Bearer API key. Programmatic access to the World API needs a key; browsing nosible.world in a browser does not.

Example: Bearer nos_sk_...

Parameters

query & path

viewenumquery

The record each event is returned as: lite (the default), the event without its evidence, or full, the complete record. Any other value is a 422 validation_error. About records on Event details lists both.

Example: lite

include_vectorbooleanquery

true adds each event's embedding, oai_vector (3,072 values, comma-separated), to either view. Defaults to false.

Example: false

datedaterequiredpath

Archive date in YYYY-MM-DD format.

Example: 2026-07-20

event_idstringrequiredpath

Canonical event identifier.

Example: 2026-07-20_en_JP_v1_NQA5mXKS5x7MUUbwQAAAABDCQAAAInpsKAEpoAAAAAA_ehrkVV2W

How to use this endpoint

guidance

Fetch event detail after discovery. The detail record is the source of truth for a factual claim: it includes the narrative, classifications, entities, coverage counters, and canonical event identity.

About records

lite and full

Every World V2.0 endpoint that returns events returns each one as a record in one of two views, chosen with view: a query parameter on GET, a top-level body field on POST. The same parameter, with the same values, works on every such endpoint: events by day, Event details, Similar events, the searches (for a day, for all time and for a date range), Get Events in Trend and the entity, ticker and ontology timelines. Any other value is a 422 validation_error.

lite, the default, is the event without its evidence: the fields listed below, about 5 KB an event. Lists, searches and timelines need nothing more. full is the complete record, as this page lists it: lite plus provenance (the supporting source documents and their snippets), availability (source documents per hour), triples (the relationships the event states), each ticker's why and v2_preview_success; about 60 KB an event, most of it provenance.

include_vector=true adds the event's embedding, oai_vector, to either view. Every response names its view in view, right after schema (first when there is no schema), and echoes include_vector when it was asked for.

Search and similarity results keep their per-result fields next to the record's own: _score, _semantic_score, _lexical_score, _retrieval and _search_date on the searches and Get Events in Trend; similarity and retrieval on Similar events; date, score, vector_scores and score_vector_scores on date-grouped search.

The fields of a lite record:

event_idstring

Stable event identifier.

versionstring

Event record version: "2.0-preview".

eventobject

The event in its original language: date, language, title, description and points.

event.datedate

World archive date of the event.

event.languagestring

ISO 639-1 code of the event's original language.

event.titlestring

Headline, in the original language.

event.descriptionstring

Short narrative, in the original language.

event.pointsstring[]

Key facts of the event, one sentence each.

englishobject

The event in English: title, description and points, translated when the original language is not English.

coverageobject

total_coverage, total_netlocs, coverage_concentration_index, first_seen, last_seen and most_seen, as in Event details.

locationsobject[]

Places of the event, its own place first, then places named in it, as in Event details.

signalsobject

Sentiment, materiality, time horizon and forward-looking signals with their class probabilities, as in Event details.

tickersobject[]

Listed companies the event concerns, in the Event details format without why. Empty when has_tickers is false.

has_tickersboolean

Whether tickers is non-empty.

entitiesobject

Named entities by NER type, {TYPE: [{name, mention_count, confidence}]}, as in Event details.

sentimentsobject

Entity-level sentiment grouped by entity type. Each item has name, sentiment_label (positive, neutral or negative), and sentiment_score, the final Percentage Margin Z-score.

ontologiesobject[]

Classifications of the event, most probable first, as in Event details.

Response body

application/json

These are the fields you can build against. Nested names use dot notation; optional sections are called out in their descriptions.

viewstring

The view the events are returned in: lite (the default) or full. See About records on Event details.

include_vectorboolean

true when the request asked for the embedding with include_vector=true; absent otherwise.

event_idstring

Stable event identifier. The same event has the same identifier in V1.2.

versionstring

Event record version: "2.0-preview".

eventobject

The event in its original language: date, language, title, description and points.

event.datedate

World archive date of the event.

event.languagestring

ISO 639-1 code of the event's original language.

event.titlestring

Headline, in the original language.

event.descriptionstring

Short narrative of the event, in the original language.

event.pointsstring[]

Key facts of the event, one sentence each, drawn from its sources.

englishobject

The event in English: title, description and points translated when the original language is not English, identical to event otherwise. english.date and english.language repeat the event's own.

english.titlestring

Headline in English.

english.descriptionstring

Narrative in English.

english.pointsstring[]

Key facts in English.

coverageobject

How widely the event was reported and when.

coverage.total_coverageinteger

Source documents (articles) in the event.

coverage.total_netlocsinteger

Distinct source sites in the event.

coverage.coverage_concentration_indexnumber

Concentration of the coverage across sites (a Herfindahl index from 0 to 1); near 1, one syndicated story dominates.

coverage.first_seendate-time

Earliest source timestamp, UTC.

coverage.last_seendate-time

Latest source timestamp, UTC.

coverage.most_seendate-time

The most frequent source timestamp, UTC (the earliest on a tie).

locationsobject[]

Places of the event. The first is the event's own place, read from its title and description (source: "llm"); the rest are places named in the event (entities of type GPE and LOC) resolved on the map (source: "ner").

locations[].continentstring

Continent of the place.

locations[].regionstring | null

Region of the place, null when unknown.

locations[].countrystring

Country of the place, as a full English name.

locations[].latnumber

Latitude.

locations[].lngnumber

Longitude.

locations[].sourcestring

How the place was found: llm for the event's own place, ner for a named place.

locations[].matched_onstring

What the place was matched on: {event.title}+{event.description} for the event's own place, otherwise the entity name.

locations[].entity_typestring

NER type of the named place (GPE or LOC); absent on the event's own place.

signalsobject

Sentiment, materiality, time horizon and forward-looking signals, with the class probabilities behind each label.

signals.sentimentstring

positive, neutral or negative: the material impact on the event's main subject, not the tone of the prose.

signals.sentiment_prob_positivenumber

Probability of positive sentiment. The three sentiment probabilities sum to 1.

signals.sentiment_prob_neutralnumber

Probability of neutral sentiment.

signals.sentiment_prob_negativenumber

Probability of negative sentiment.

signals.materialitystring

high, medium or low, bucketed from materiality_score at 0.60 and 0.30.

signals.materiality_scorenumber

Continuous materiality from 0 to 1.

signals.time_horizonstring

intraday, days, weeks, months, quarters or years.

signals.forward_lookingstring

forward or not-forward.

signals.forward_looking_prob_forwardnumber

Probability that the event is forward-looking.

signals.forward_looking_prob_not_forwardnumber

Probability that it is not.

tickersobject[]

Listed companies the event concerns, mapped through the Atlas graph, strongest first. Empty when has_tickers is false.

tickers[].tickerstring

Symbol with its exchange suffix, such as NVDA.US.

tickers[].companyv5_idstring

NOSIBLE company identifier of the issuer.

tickers[].namestring

Issuer name.

tickers[].websitestring

Issuer website.

tickers[].wiki_qidstring

Wikidata identifier of the issuer.

tickers[].isinstring

ISIN of the security.

tickers[].leistring

LEI of the issuer.

tickers[].figistring

FIGI of the security.

tickers[].sectorstring

GICS sector of the issuer.

tickers[].industrystring

GICS industry of the issuer.

tickers[].country_isostring

ISO 3166-1 alpha-2 country of the issuer.

tickers[].exchangestring

Exchange of the listing.

tickers[].micstring

ISO 10383 market identifier code of the exchange.

tickers[].scorenumber

Strength of the link between the event and the company, from 0 to 1.

has_tickersboolean

Whether tickers is non-empty.

entitiesobject

Named entities in the event by NER type (PERSON, ORG, GPE, LOC, PRODUCT, ...). Each type lists {name, mention_count, confidence}: the name as written in the sources, how often it is mentioned and the recognizer's confidence from 0 to 1.

sentimentsobject

Entity-level sentiment grouped by entity type. Each item has name, sentiment_label (positive, neutral or negative), and sentiment_score, the final Percentage Margin Z-score.

triples[].subjectstring

Subject entity.

triples[].subject_typestring

NER type of the subject.

triples[].predicatestring

Relationship type, such as collaborates_with or ceo_of.

triples[].objectstring

Object entity.

triples[].object_typestring

NER type of the object.

triples[].original_scorenumber

Confidence of the relation extractor.

triples[].reranker_scorenumber

Confidence after reranking.

ontologiesobject[]

Classifications of the event, one per taxonomy that classified it, most probable first. Each names its taxonomy in ontology, carries that taxonomy's slots (label for a flat taxonomy; tier_1 to tier_4, sector to sub_industry, category / subcategory / event and so on for the others) and the probability. A taxonomy that did not classify the event is absent, and so is a slot it left empty.

ontologies[].ontologystring

Taxonomy, named as in the World Search filter fields: iab, gics, nosible, media_frame, ekman7_emotion, schema_org_event and so on.

ontologies[].probabilitynumber

Probability of the classification.

provenance[].event_scorenumber

Relevance of the document to the event, from 0 to 1.

provenance[].urlstring

Document URL.

provenance[].titlestring

Document title.

provenance[].descriptionstring

Document description.

provenance[].snippetsstring[]

Passages of the document that support the event.

tickers[].whyobject[]

view=full only. The reasons for the link, strongest first: an entity in the event and the graph relationships that lead from it to the issuer.

availabilityobject

view=full only. Source documents per UTC hour, as in Event details.

triplesobject[]

view=full only. Relationships between entities stated in the event, as in Event details.

provenanceobject[]

view=full only. Supporting source documents with their snippets, as in Event details.

v2_preview_successboolean

view=full only. Whether the V2.0 pipeline completed the event.

oai_vectorstring

Only with include_vector=true: the event's 3,072-dimension embedding (text-embedding-3-large), comma-separated.

Responses and errors

HTTP

200Request succeeded. The response body is shown in the panel on the right.

400invalid_json — The request body is not JSON. Every error body, 401 included, is {error, message, status}.

401api_key_required — No API key was sent. Send it as Authorization: Bearer <key> or the api-key header.

401invalid_api_key — The API key is invalid or has been revoked.

403access_denied — The requested archive date is outside the caller's World tier.

422validation_error — The request is well formed but the API cannot decode or validate it: an unknown body field or query parameter, a missing required parameter, a value of the wrong type, an empty and, or or not, a date that is not a calendar date (in the path, the query or the body), an unknown enum value or a reversed range. The message names the parameter and what is wrong.

404not_found — The requested date, entity, ticker, or event does not exist in the accessible index.

410cursor_expired — The cursor was minted against a replaced index build. Restart pagination from the first page.

429rate_limited — The request exceeded the endpoint or account rate limit. Respect Retry-After when supplied.

501backend_not_configured — The World backend is not configured for this deployment.

503api_key_auth_unavailable — API key authentication is temporarily unavailable; retry shortly.

503api_key_metering_unavailable — API key usage metering is temporarily unavailable, so the request was not served; wait for the Retry-After header (30 seconds) and retry.

502backend_error — The World backend could not be reached or did not return a valid response; retry shortly.

504backend_timeout — The World backend did not answer within 300 seconds; narrow the request (for example with a date window) or retry.