96b9b942e6
Disciplined Path β (field decode α was empirically falsified). Reads S-P-O
structure SYMBOLICALLY from the token sequence via domain-agnostic templates
keyed on FUNCTION WORDS + ORDER, mints content as MeaningGraph entities/relations,
parse-or-refuse (wrong=0 at the comprehension layer).
Templates (set_membership): 'X is a Y' -> member; 'all Xs are Ys' -> subset;
'is X a Y?' / 'are all Xs Ys?' -> queries; definite-NP ('the X is a Y');
conservative singularization incl. irregulars (people->person), refusing
unknown morphology rather than guessing.
End-to-end: prose -> comprehend -> project -> INDEPENDENT set_membership oracle
-> answer vs gold. Result on the real v1 lane: 8 correct / 0 wrong / 0 refused
(full coverage, wrong=0). Cross-content generality (animals/professions/geography)
asserted. 14 reader unit tests + 3 end-to-end tests, each bites under its
violation. Additive only; invariants + capability index green.
8 lines
473 B
Python
8 lines
473 B
Python
"""Comprehension scoring lanes — the engine reader under test, scored end-to-end
|
|
against the staged independent-gold lanes (Phase 2a, COMPREHEND).
|
|
|
|
Unlike the ``evals/<domain>`` gold-only lanes (which verify oracle/gold integrity),
|
|
these runners drive the general comprehension reader over the lane PROSE and score
|
|
its output through the lane's INDEPENDENT oracle. wrong=0 is the floor: the reader
|
|
must refuse rather than emit a structure that yields a wrong answer.
|
|
"""
|