Dontopedia
Explore

Eval Dataset

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-11.)

Eval Dataset has 10 facts recorded in Dontopedia across 6 references, with 2 live disagreements.

10 facts·7 predicates·6 sources·2 in dispute

Mostly:rdf:type(3), used for(2), referenced but not defined(1)

Maturity scale raw canonical shape-checked rule-derived certified

Rdf:typein disputerdf:type

Used forin disputeusedFor

  • Model Evaluation[2]sourceall time · Aaa2ab69 D393 49d6 B565 40f47c0bccb9
  • model_evaluation[6]sourceall time · 6c3b0310 9572 42f3 A33f 3f41bc304470

Referenced But Not DefinedreferencedButNotDefined

  • true[3]all time · F0656b10 4efe 4bd0 9005 6e894f93f6b4

Derived From SplitderivedFromSplit

  • test[1]sourceall time · 04edfc72 1f93 4ce7 B6df 887c9a5f1db3

Derived FromderivedFrom

  • Dataset[1]all time · 04edfc72 1f93 4ce7 B6df 887c9a5f1db3

Is Used byisUsedBy

  • Trainer[2]sourceall time · Aaa2ab69 D393 49d6 B565 40f47c0bccb9

Used byusedBy

  • Trainer[5]sourceall time · 09c69473 903c 475d 98c1 A87aeedbce93

Inbound mentions (7)

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.

configuredWithConfigured With(1)

createsCreates(1)

hasParticipantHas Participant(1)

inverseOfInverse of(1)

requiresRequires(1)

takesParameterTakes Parameter(1)

usesUses(1)

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.

10 undated
—
derivedFrombeam/04edfc72-1f93-4ce7-b6df-887c9a5f1db3
ex:dataset
—
derivedFromSplitbeam/04edfc72-1f93-4ce7-b6df-887c9a5f1db3
test
—
isUsedBybeam/aaa2ab69-d393-49d6-b565-40f47c0bccb9
ex:Trainer
—
typebeam/f0656b10-4efe-4bd0-9005-6e894f93f6b4
ex:Dataset
—
typebeam/04edfc72-1f93-4ce7-b6df-887c9a5f1db3
ex:DatasetVariable
—
typebeam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0
ex:Parameter
—
referencedButNotDefinedbeam/f0656b10-4efe-4bd0-9005-6e894f93f6b4
true
—
usedBybeam/09c69473-903c-475d-98c1-a87aeedbce93
ex:trainer
—
usedForbeam/aaa2ab69-d393-49d6-b565-40f47c0bccb9
ex:model_evaluation
—
usedForbeam/6c3b0310-9572-42f3-a33f-3f41bc304470
model_evaluation

References (6)

6 references
  1. [1]beam-chunk3 facts
    customctx:claims/beam/04edfc72-1f93-4ce7-b6df-887c9a5f1db3
    • full textbeam-chunk
      text/plain1 KBdoc:beam/04edfc72-1f93-4ce7-b6df-887c9a5f1db3
      Show excerpt
      from transformers import ( AutoModelForSequenceClassification, AutoTokenizer, Trainer, TrainingArguments, DataCollatorWithPadding, ) from datasets import load_dataset, DatasetDict # Load the model and tokenizer model_na…
  2. [2]beam-chunk2 facts
    customctx:claims/beam/aaa2ab69-d393-49d6-b565-40f47c0bccb9
    • full textbeam-chunk
      text/plain1 KBdoc:beam/aaa2ab69-d393-49d6-b565-40f47c0bccb9
      Show excerpt
      errors.append(doc) return errors errors = analyze_tokenization_errors(documents, tokenizer) print(f"Tokenization Errors: {errors}") # Fine-tune the model on your specific dataset # This involves preparing a labeled dataset…
  3. [3]beam-chunk2 facts
    customctx:claims/beam/f0656b10-4efe-4bd0-9005-6e894f93f6b4
    • full textbeam-chunk
      text/plain1 KBdoc:beam/f0656b10-4efe-4bd0-9005-6e894f93f6b4
      Show excerpt
      train_dataset=train_dataset, eval_dataset=eval_dataset, tokenizer=tokenizer, data_collator=DataCollatorWithPadding(tokenizer), ) # Fine-tune the model trainer.train() # Define the feedback analysis logic def analyze_feedba…
  4. [4]beam-chunk1 fact
    customctx:claims/beam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0
    • full textbeam-chunk
      text/plain1 KBdoc:beam/97ef0996-2bbf-4217-af6b-6a0f7a933ea0
      Show excerpt
      eval_dataset=eval_dataset, ) trainer.train() ``` ### Evaluation Metrics To evaluate the quality of reformulated queries, you can use metrics like BLEU or ROUGE: ```python from nltk.translate.bleu_score import sentence_bleu def eval…
  5. [5]beam-chunk1 fact
    customctx:claims/beam/09c69473-903c-475d-98c1-a87aeedbce93
    • full textbeam-chunk
      text/plain1 KBdoc:beam/09c69473-903c-475d-98c1-a87aeedbce93
      Show excerpt
      output_dir='./results', num_train_epochs=3, per_device_train_batch_size=8, per_device_eval_batch_size=8, warmup_steps=500, weight_decay=0.01, logging_dir='./logs', logging_steps=10, evaluation_strategy="s…
  6. [6]beam-chunk1 fact
    customctx:claims/beam/6c3b0310-9572-42f3-a33f-3f41bc304470
    • full textbeam-chunk
      text/plain1 KBdoc:beam/6c3b0310-9572-42f3-a33f-3f41bc304470
      Show excerpt
      logging_steps=10, evaluation_strategy='epoch', save_total_limit=2, ) # Define the trainer trainer = Trainer( model=model, args=training_args, train_dataset=dataset['train'], eval_dataset=dataset['test'], dat…

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.

↑