robbond
f94d47d813
docs: record uncertainty proposition coverage
2026-08-14 06:16:14 +01:00
robbond
4e66e1ffbf
experiment: validate clean proposition question live
2026-08-13 17:54:04 +01:00
robbond
802eb1cc16
docs: record proposition question formulation fix
2026-08-13 17:45:28 +01:00
robbond
4a434bb939
experiment: diagnose proposition question shape
2026-08-13 17:30:50 +01:00
robbond
60036ac495
experiment: validate proposition-specific decision question live
2026-08-13 17:09:17 +01:00
robbond
4767de30f7
docs: record audience question routing fix
2026-08-13 16:58:32 +01:00
robbond
ea7f227974
experiment: diagnose material-question specificity
2026-08-13 13:15:22 +01:00
robbond
229fbfbfd9
experiment: test decision chain across product launch
2026-08-13 13:04:09 +01:00
robbond
43b9e5a35c
experiment: validate bounded structural context admission live
2026-08-13 12:56:20 +01:00
robbond
a7ca8d712d
docs: record bounded structural context admission
2026-08-13 12:49:42 +01:00
robbond
7f97268f68
experiment: define structural reasoning-context embedding
2026-08-13 10:26:54 +01:00
robbond
48de8b6ce7
experiment: choose reasoning-pattern inheritance boundary
2026-08-13 10:14:19 +01:00
robbond
32e668969e
experiment: diagnose decision-pattern kind mismatch
2026-08-13 09:54:42 +01:00
robbond
3a4dda9daf
experiment: validate prerequisite-aware question targeting live
2026-08-13 09:45:13 +01:00
robbond
3c6e436e89
docs: record prerequisite-aware question targeting
2026-08-13 09:36:10 +01:00
robbond
854c3aa002
experiment: choose material-factor question alignment
2026-08-13 07:57:26 +01:00
robbond
d1fe4ca087
experiment: diagnose material-factor question targeting
2026-08-13 07:49:37 +01:00
robbond
721f1ccb6e
experiment: test materiality rule against real unresolved factor
2026-08-13 07:41:09 +01:00
robbond
e8e6986d15
experiment: validate decision materiality rule live
2026-08-13 07:33:52 +01:00
robbond
b671681ddc
docs: record decision materiality rule
2026-08-13 07:24:18 +01:00
robbond
5dcaed39df
experiment: diagnose decision sufficiency rule
...
Read-only inspection of 8 files (prompt-builder.js, schema.js, utils.js,
apply-proposal.js, orchestrator.js, experiment-60b1.md, experiment-60b2.md,
current-handoff.md). No code changes.
Key findings:
- Prompt has no independent materiality/sufficiency rule (Rule 20 says null
selectedQuestion when 'no consequential unresolved unknown' but doesn't define
what makes an unknown non-consequential)
- Validator performs structural checks only, no evidence sufficiency evaluation
- No cross-option comparison logic in propagateResolvedChildEvidence
- Schema has no materiality or couldChangeDecision field
- 60B.1 resolved WITH 'no other material differences' cue; 60B.2 continued
WITHOUT it, despite internally computing ~3.6 month payback
Classification: C — NO SUFFICIENCY RULE + CONTINUATION BIAS
Missing distinction: MATERIALITY / DECISION-RELEVANCE RULE
2026-08-13 07:15:01 +01:00
robbond
306f8392a1
experiment: test independent decision sufficiency
2026-08-13 06:47:10 +01:00
robbond
60a1befff7
experiment: test decision sufficiency on option graph
2026-08-13 06:39:12 +01:00
robbond
18979e229b
experiment: test downstream option evidence update
2026-08-13 06:30:24 +01:00
robbond
4c25faaa01
feat(60A.7): add reusable decision-options fixture loading in test harness
...
- Load decisions-options fixture from committed JSON (tests/fixtures/
pre-anchored-decision-options.json) instead of inline duplicate
- Add runPreAnchoredSimulationWithFixture() helper for decision-options
mode tests
- Generalize anchor validation from savings-realism-specific to generic
unresolved unknown check in reproduce-multi-turn-investigation.mjs
- Add experiment documentation (experiment-60a7.md) and handoff note
- All 63 harness tests pass; no production reasoning code changed
2026-08-13 06:24:12 +01:00
robbond
2016a024c5
experiment: rerun option consequence structure once
2026-08-13 06:08:23 +01:00
robbond
56a04ddd0e
experiment: test option-specific consequence structure
2026-08-13 05:53:20 +01:00
robbond
3db6f40fdc
experiment: validate native option structure live
2026-08-12 19:49:02 +01:00
robbond
6dd9afbf6b
experiment: choose minimum decision representation
2026-08-12 18:34:18 +01:00
robbond
e6cf973d2a
exp 60A.1: read-only vocabulary adequacy diagnosis for alternatives and decisions
...
Diagnoses the root cause of the persistent pattern from 59B.2-59B.4
where explicit dual-option input collapsed into a single undifferentiated
unknown node. Concludes the graph vocabulary lacks first-class primitives
for options/decisions (not primarily a prompt issue). Identifies three
missing primitives: option node kind, decision node kind, alternative_of
edge type. Recommends ~25-line schema addition for 60A.2 implementation.
2026-08-12 18:19:29 +01:00
robbond
ec32713c31
experiment: test explicit two-option decision structure
2026-08-12 17:52:38 +01:00
robbond
2cd346423d
experiment: test do-nothing baseline representation
2026-08-12 17:42:25 +01:00
robbond
70688f91c9
experiment: test independent decision relevance
2026-08-12 17:18:18 +01:00
robbond
7f27fccadc
experiment: test decision relevance and do-nothing baseline
2026-08-12 17:10:01 +01:00
robbond
8856e66147
experiment: test known-vs-uncertain consequence structure
2026-08-12 16:59:56 +01:00
robbond
c3c5351143
experiment: test trade-off decomposition
2026-08-12 16:51:39 +01:00
robbond
8c5c4b5b75
experiment: test shift into trade-off reasoning
2026-08-12 16:37:52 +01:00
robbond
3f1bf7bcb0
experiment: test verified uncertainty resolution
2026-08-12 16:26:43 +01:00
robbond
52c529a688
experiment: test qualified evidence uncertainty status
2026-08-12 16:02:28 +01:00
robbond
201f259326
experiment: exercise interrogative question rendering live
2026-08-12 15:35:00 +01:00
robbond
6f2c09cd94
experiment: validate question-formulation fix live
2026-08-12 15:29:38 +01:00
robbond
870d6caa05
docs: record question-formulation fix
2026-08-12 15:07:13 +01:00
robbond
b1914f5da7
experiment: test next-question formulation
2026-08-12 13:53:03 +01:00
robbond
20e4b58440
experiment: test evidence preservation with one uncertainty
2026-08-12 13:46:29 +01:00
robbond
32184694c5
experiment: test qualified-answer reasoning
2026-08-12 13:35:40 +01:00
robbond
a78f3edb10
experiment: choose declaration recovery boundary
2026-08-12 13:27:02 +01:00
robbond
a40a3e343e
experiment: diagnose null semantic mutation path
2026-08-12 13:19:37 +01:00
robbond
eaf3194752
experiment: observe direct meaning/action fields on anchored update
2026-08-12 12:09:32 +01:00
robbond
6a04d62800
docs: record accepted answer-meaning capture
2026-08-12 12:01:16 +01:00
robbond
d2891730af
experiment: rerun incremental meaning on anchored uncertainty
2026-08-12 11:19:47 +01:00
robbond