Dontopedia

Last Hidden State Extraction

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-10.)

Last Hidden State Extraction has 5 facts recorded in Dontopedia across 2 references.

5 facts·5 predicates·2 sources

Mostly:uses slicing(1), calls detach(1), calls numpy(1)

Maturity scale raw canonical shape-checked rule-derived certified

Other facts (5)

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.

5 facts
PredicateValueRef
Uses Slicing[:, 0, :][1]
Calls DetachDetach[1]
Calls NumpyNumpy[1]
Rdf:typeTensor Slicing[2]
ExtractsFirst Token[2]

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.

usesSlicingbeam/56b422f7-45b6-49d7-9022-6df268bf77c3
[:, 0, :]
callsDetachbeam/56b422f7-45b6-49d7-9022-6df268bf77c3
ex:detach
callsNumpybeam/56b422f7-45b6-49d7-9022-6df268bf77c3
ex:numpy
typebeam/24776806-43b0-491e-806d-e4f4e8d75851
ex:TensorSlicing
extractsbeam/24776806-43b0-491e-806d-e4f4e8d75851
ex:first-token

References (2)

2 references
  1. ctx:claims/beam/56b422f7-45b6-49d7-9022-6df268bf77c3
    • full textbeam-chunk
      text/plain1 KBdoc:beam/56b422f7-45b6-49d7-9022-6df268bf77c3
      Show excerpt
      inputs = tokenizer(document, return_tensors='pt') outputs = model(**inputs) return outputs.last_hidden_state[:, 0, :].detach().numpy() # vectorize 10K documents documents = [...] # list of 10K documents vectors = [vectorize_do
  2. ctx:claims/beam/24776806-43b0-491e-806d-e4f4e8d75851

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.