e831ed2615
Phase 2a r2/r3/r4 of the redefined plan: the general comprehension reader now
reads THREE independent-gold reasoning domains end-to-end (prose -> MeaningGraph
-> projection -> independent oracle -> answer vs gold), all wrong=0, and all
three are wired into the capability index.
reader.py — new domain-agnostic templates (function words + order; parse-or-refuse):
- categorical E/I/O: "no Xs are Ys"->disjoint, "some Xs are Ys"->intersects,
"some Xs are not Ys"->some_not (A "all Xs are Ys"->subset already existed)
- "therefore <categorical>" -> conclusion QUERY (same neutral predicate vocab)
- comparative facts: "<X> [is] <comp> [than] <Y>" -> less(...), closed
less/greater comparator lexicon, elided-copula support
- sort query ("sort ascending|descending", "... order from <low> to <high>")
and compare query ("compare <X> with <Y>")
- clause-splitting on commas / leading and|or for multi-clause sentences
projectors.py — to_syllogism (premises + validity conclusion, finite-model size 3)
and to_total_ordering (less-facts + sort/compare). Both return None when nothing
is honestly askable of their oracle (caller treats as refusal).
capability_index — wire 3 comprehension lanes into ADAPTERS; re-freeze baseline
breadth 3->6, capability_score 0.919641->0.814356 (geomean falls BY DESIGN as
honest partial-coverage domains join; wrong_total stays 0). digest 0a98b9b4...
Scores: set_membership 8/8, syllogism 6/8, total_ordering 4/8 — all wrong=0.
Multi-word NP handling is DEFERRED on purpose, not missed: the gold lanes
canonicalize multi-word NPs three contradictory ways ("North station"->"north",
"Level one"->"level_one", "metal objects"->"metal"), so no single general rule is
wrong=0-safe. The reader refuses multi-word NPs until the gold lanes carry a
canonicalization contract. Every refusal is a genuine harder phenomenon
(multi-word NP, adjectival predicate, trailing tokens) — never a readable case
silently dropped.
Tests: reader templates, projector unit tests, syllogism/total_ordering
end-to-end wrong=0 with pinned counts, capability breadth 3->6. 138 targeted +
87 smoke green. Lane SHAs 8/9 (sole miss = public_demo env wall-clock flake).
62 lines
1.3 KiB
JSON
62 lines
1.3 KiB
JSON
{
|
|
"capability_score": 0.814356,
|
|
"coverage_geomean": 0.814356,
|
|
"coverage_micro": 0.988266,
|
|
"accuracy_micro": 1.0,
|
|
"breadth": 6,
|
|
"min_domain_coverage": 0.5,
|
|
"wrong_total": 0,
|
|
"assert_mode_valid": true,
|
|
"deterministic_digest": "0a98b9b41c23f5166d7e23bc194207ead53a89d5316dddc03194bd2739bb9753",
|
|
"domains": [
|
|
{
|
|
"domain": "comprehension_set_membership",
|
|
"correct": 8,
|
|
"wrong": 0,
|
|
"refused": 0,
|
|
"coverage": 1.0,
|
|
"accuracy": 1.0
|
|
},
|
|
{
|
|
"domain": "comprehension_syllogism",
|
|
"correct": 6,
|
|
"wrong": 0,
|
|
"refused": 2,
|
|
"coverage": 0.75,
|
|
"accuracy": 1.0
|
|
},
|
|
{
|
|
"domain": "comprehension_total_ordering",
|
|
"correct": 4,
|
|
"wrong": 0,
|
|
"refused": 4,
|
|
"coverage": 0.5,
|
|
"accuracy": 1.0
|
|
},
|
|
{
|
|
"domain": "deductive_logic",
|
|
"correct": 716,
|
|
"wrong": 0,
|
|
"refused": 0,
|
|
"coverage": 1.0,
|
|
"accuracy": 1.0
|
|
},
|
|
{
|
|
"domain": "dimensional",
|
|
"correct": 10,
|
|
"wrong": 0,
|
|
"refused": 2,
|
|
"coverage": 0.833333,
|
|
"accuracy": 1.0
|
|
},
|
|
{
|
|
"domain": "relational_metric",
|
|
"correct": 14,
|
|
"wrong": 0,
|
|
"refused": 1,
|
|
"coverage": 0.933333,
|
|
"accuracy": 1.0
|
|
}
|
|
],
|
|
"not_covered": []
|
|
}
|