Przejdź do treści

← All commands

chimera decide

Ask typed questions — yes/no, a choice, a score — and get probabilities back. Every question is read on its own, decision-first; a question the linter rejects is refused before any call. `noul` is P(yes); `confidence` describes how peaked the probabilities are and is not a probability of being right. A number is calibrated only where a map exists for exactly this question. Measured on a ruler we did not build (`bench/jevbench_local`, the 231 public JevBench items): the default local backend answers 0.619 of them right (Jev 1.13: 0.866), 0.324 on the hard tier, with a raw top-label ECE of 0.218. Options that share a first token cannot be read locally: name them so their first words differ.

Options

  • --questions, -qstrrequired

    JSON file: the questions (request shape, no state).

  • --state, -sstrdefault: ''

    The state to ask about.

  • --jsonlstr

    Ask about every line of this JSONL file instead.

  • --fieldstrdefault: 'state'

    With --jsonl: the field that holds the state.

  • --out, -ostr

    With --jsonl: write results here (default: stdout).

  • --decisionstrdefault: ''

    Name the decision (the key a calibration map is found by).

  • --no-logboolean

    Do not write the answers to the decision log.