From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-11.)
Max Length has 18 facts recorded in Dontopedia across 8 references, with 4 live disagreements.
Mostly:rdf:type(5), rdfs:label(3), has value(2)
hasValueappliedTohasDefaultparameterValuereferencesdefaultParameterValueOther 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.
hasArgumentHas Argument(3)ex:callex:model_generateex:tokenizer_callhasParameterHas Parameter(3)ex:__init__ex:__init__ex:model.generatehasConstraintTypeHas Constraint Type(2)ex:field2-constraintex:field7-constraintchecksKeyPresenceChecks Key Presence(1)ex:constraint-checkex:usesVariableEx:uses Variable(1)ex:masking-codehasMaxLengthHas Max Length(1)ex:constraintsusesUses(1)ex:tokenizationTimeline 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.
doc:beam/14cf4eab-a053-4cf0-b374-9022e5e69c19model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=len(df['label'].unique())) tokenizer = AutoTokenizer.from_pretrained(model_name) # Tokenize the data train_encodings = tokenizer(train_df['query'].tolist(), …
doc:beam/cc213d9b-9051-49f2-ac29-2090be7dfaeamodel = T5ForConditionalGeneration.from_pretrained('./fine_tuned_model') def reformulate_query(query): inputs = tokenizer(f"reformulate: {query}", return_tensors="pt", max_length=512, truncation=True) outputs = model.generate(input…
doc:beam/8a3d9053-ab82-4206-8ea2-43c648648492Your current implementation uses `np.argmax(outputs.logits)` which suggests you are treating the reformulation as a classification problem. However, query reformulation is often better handled as a sequence-to-sequence task. Instead of clas…
Dontopedia is in a read-only public launch. Follow the references and disputed branches now; contributions will open after durable identity and moderation are in place.