Course / Lectures / Lecture 06 / Lab Lab 06

The interface selector.

Five requirements in, five interfaces out. The ranking is a documented rule table, not a learned model: change one input and the reason changes. The point is to make the design space explicit, not to pick for you.

5 inputs 5 interfaces 0 external requests Deterministic · reset returns to defaults

The interface selector

1 · Data type
2 · Supervision
3 · Formal guarantee
4 · Compute budget
5 · Is the symbolic model trustworthy?

Defaults: perception · weak supervision · guarantee preferred · high budget · partly trusted.

Ranked shortlist

Points are rule weights, not probabilities, benchmark scores, or a recommendation. The bar is relative to this shortlist.

Choose the five inputs; the shortlist updates immediately.

    How the score was built

    Every row is a rule that fired. The total is the sum of the rows, and the ranking is the total with a fixed tie-break.

    THE RULES

    Five inputs, a small table, no hidden model.

    The selector adds points from five rows: one base row for the data type and one row for each of the other four inputs, plus a fixed tie-break. The tables below are generated from the same object the selector uses.

    What the points are not

    They are not learned weights, not calibrated probabilities, and not estimates of success. They encode the lecture’s qualitative trade-offs so that the ranking can be inspected. A different team with different costs should change the weights — and then defend the change.

    WHAT TO NOTICE

    The shortlist moves with the requirement.

    WHAT THIS SHOWS · 01

    The design space is small

    Five interfaces, five inputs, and a handful of interactions. Most of the argument about a neurosymbolic design is an argument about which row should dominate — not about which brand to use.

    WHAT THIS SHOWS · 02

    Requirements trade off

    A required guarantee pushes the verifier and search up and the soft loss down. A low budget pushes search down. An untrusted symbolic model pushes hard constraints down. The movement is the lesson.

    WHAT THIS DOES NOT · 01

    It is not a benchmark

    The points are not measured. The selector knows nothing about your data, your latency, your team, or your failure costs. It cannot tell you which shortlisted design will work.

    WHAT THIS DOES NOT · 02

    It is not a recommendation

    A high score is a hypothesis about fit, not a verdict. The honest output is a shortlist plus a reason, and the next step is an ablation, not a commitment.

    Three settings worth trying

    1. Perception · weak · required · low · no. A hard guarantee is wanted, the symbolic model is suspect, and there is no budget for search. Read the trace: which interface survives, and what does the reason admit?
    2. Language · none · required · high · yes. The classic proposal-and-check setting. Search and verifier should rise; compare their reasons and their trade-offs.
    3. Graph · full · not needed · low · yes. The structure is the supervision and the deployment is cheap. The data interface should dominate; ask what it still cannot guarantee.

    Back to the selection procedure · Read the guarantee taxonomy again · Open the slides