Dontopedia

bert-base-uncased

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-09.)

bert-base-uncased has 20 facts recorded in Dontopedia across 5 references, with 2 live disagreements.

20 facts·12 predicates·5 sources·2 in dispute

Mostly:rdf:type(6), is variant of(2), has tokenizer(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (5)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

constructorArgumentConstructor Argument(1)

initializesModelInitializes Model(1)

loadsLoads(1)

usesUses(1)

usesModelUses Model(1)

Other facts (18)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

18 facts
PredicateValueRef
Rdf:typeMachine Learning Model[1]
Rdf:typePretrained Model[1]
Rdf:typeEmbedding Model[2]
Rdf:typeTransformer Model[3]
Rdf:typeMachine Learning Model[4]
Rdf:typeModel Instance[5]
Is Variant ofBERT model[1]
Is Variant ofBert Model[3]
Has TokenizerBert Base Uncased Tokenizer[1]
Has Namebert-base-uncased[3]
RequiresBert Base Uncased Tokenizer[3]
Has Sizelarge[3]
CausesHigh Memory Usage[3]
Loaded ViaFrom Pretrained Method[3]
Used byModel Inference Service Instance[4]
Source Code Line1[4]
Member ofSource Document[4]
Is InstanceMachine Learning Model[4]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

typebeam/303c0de1-022c-4e96-98b8-fc4abf6b16f1
ex:MachineLearningModel
hasTokenizerbeam/303c0de1-022c-4e96-98b8-fc4abf6b16f1
ex:bert-base-uncased-tokenizer
typebeam/303c0de1-022c-4e96-98b8-fc4abf6b16f1
ex:PretrainedModel
isVariantOfbeam/303c0de1-022c-4e96-98b8-fc4abf6b16f1
BERT model
typebeam/255cb48f-250c-4d37-87ab-fa0c34c3ca48
ex:EmbeddingModel
labelbeam/255cb48f-250c-4d37-87ab-fa0c34c3ca48
bert-base-uncased
typebeam/a8168006-9202-4429-b24c-e5dcb90b00ff
ex:TransformerModel
hasNamebeam/a8168006-9202-4429-b24c-e5dcb90b00ff
bert-base-uncased
requiresbeam/a8168006-9202-4429-b24c-e5dcb90b00ff
ex:bert-base-uncased-tokenizer
isVariantOfbeam/a8168006-9202-4429-b24c-e5dcb90b00ff
ex:bert-model
hasSizebeam/a8168006-9202-4429-b24c-e5dcb90b00ff
large
causesbeam/a8168006-9202-4429-b24c-e5dcb90b00ff
ex:high-memory-usage
loadedViabeam/a8168006-9202-4429-b24c-e5dcb90b00ff
ex:from_pretrained-method
typebeam/6aefea5d-5816-4047-8483-d50ca36e6c6c
ex:MachineLearningModel
labelbeam/6aefea5d-5816-4047-8483-d50ca36e6c6c
bert-base-uncased
usedBybeam/6aefea5d-5816-4047-8483-d50ca36e6c6c
ex:model-inference-service-instance
sourceCodeLinebeam/6aefea5d-5816-4047-8483-d50ca36e6c6c
1
memberOfbeam/6aefea5d-5816-4047-8483-d50ca36e6c6c
ex:source-document
isInstancebeam/6aefea5d-5816-4047-8483-d50ca36e6c6c
ex:MachineLearningModel
typebeam/42f279b2-a34b-446e-9204-29e263d7a929
ex:ModelInstance

References (5)

5 references
  1. ctx:claims/beam/303c0de1-022c-4e96-98b8-fc4abf6b16f1
    • full textbeam-chunk
      text/plain1 KBdoc:beam/303c0de1-022c-4e96-98b8-fc4abf6b16f1
      Show excerpt
      [Turn 544] User: Sure, let's proceed with the implementation you outlined. It looks good and should help us meet the deadline. I'll start by implementing the context-aware retrieval function and then move on to testing it with different que
  2. ctx:claims/beam/255cb48f-250c-4d37-87ab-fa0c34c3ca48
  3. ctx:claims/beam/a8168006-9202-4429-b24c-e5dcb90b00ff
    • full textbeam-chunk
      text/plain1 KBdoc:beam/a8168006-9202-4429-b24c-e5dcb90b00ff
      Show excerpt
      - Test the pipeline to ensure it handles errors and retries correctly. - Verify that the system can handle 3,500 documents per hour with under 200ms processing time. 3. **Monitor Performance**: - Monitor the system to ensure it ac
  4. ctx:claims/beam/6aefea5d-5816-4047-8483-d50ca36e6c6c
  5. ctx:claims/beam/42f279b2-a34b-446e-9204-29e263d7a929
    • full textbeam-chunk
      text/plain1 KBdoc:beam/42f279b2-a34b-446e-9204-29e263d7a929
      Show excerpt
      from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score def evaluate(y_true, y_pred): acc = accuracy_score(y_true, y_pred) prec = precision_score(y_true, y_pred, average='weighted')

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.