Swap the floor->ceiling reference to the substrate paper (Ariahw et al. 2025),
which benchmarks interventions on the same floor (No-Intervention hack ~79%) /
ceiling (RL-Baseline no-loophole). Their best arm (Ground-Truth Penalty, ~0%
hack, perf >= ceiling) reaches the top corner BUT uses the oracle monitor at
train time -- the exact cheat our no-cheat constraint forbids; their only
oracle-free method (inoculation) gave incomplete, high-variance mitigation.
Plotted hatched/grey as an ORACLE upper bound (solve approx; figures are images,
200-step preset not step-matched). Honest framing: their working methods need
the oracle; ours uses no detector at train time and still suppresses 93%.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
select = routing precision = hack_supp - solve_supp on the knob (held-out val,
knob-ON vs knob-OFF, same split). 1.0 = removes all hacking at no solve cost.
Sanity: vanilla=0.00 (no knob), base=blank (no knob-on signal), per-token=0.96.
hack_supp = (vanilla - hack)/vanilla ; solve_uplift = (solve - base)/(ceiling - base),
the floor->ceiling normalized fractions (ceiling provisional=paper 0.223, FIXME job 24).
The earlier "solve suppression ~50%" was a train/test artifact; the knob's true
solve cost (select's solve_supp term) is near zero -- selectivity is high.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Rework per feedback: hack and solve are not opposites, so they get separate
floor->ceiling axes (each 0=floor..1=ceiling) rather than sharing a zero -- this
also stops solve (range ~0.13-0.22) being squished next to hack (0-0.61).
Minimal: routeV per-token (best) vs random-V (direction control) vs the SGTM
gradient-routing paper placed on the same floor->ceiling % axis (approx, LM task).
Reads: hack suppression 93% best / 84% control / ~98% reference (9pp = direction
signal); solve gained +17% / -17% / ~95% (far from ceiling -- model barely learns
to solve in 60 steps). Moved out/plots -> out/figs.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Two-stage script: build out/plots/floor_ceiling.csv (one row per arm/anchor,
with SOURCE and STATUS columns flagging every provisional/missing cell) then
the keynote figure. Prints TODO/FIXME data gaps before plotting.
Panel A: normalized floor->ceiling bars, headline deploy (knob-off, test n=119).
Panel B: the knob effect -- arrow knob-ON -> knob-OFF on the SAME held-out val
split (eval_curve.jsonl), isolating the quarantine from the train/test
memorization gap. Fixes the earlier conflation where the train->deploy arrow
mixed knob-on/off with train-problems/test-problems.
Data gaps flagged in csv: solve ceiling provisional=paper 0.223 (FIXME job 24),
prog_wide arm contaminated (TODO job 28 prog_wide_clean).
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
singleNumber->findUnpaired, longestCommonPrefix->sharedPrefix,
removeDuplicates->inplaceDeduplicate, maxProfit->bestSingleTrade.
Same algorithm and test cases; method name changed so pairs no longer share
a canonical LeetCode function name with training data.
Also update results.md Q14 table: add hack_train/solve_train columns,
vanilla row, and prog_wide contamination note (docs/ is gitignored).
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
- Delete src/vgrout/pairs_v2.py and src/vgrout/pairs_intent.py; move all data
into scripts/pairset_build_intent.py (self-contained, exports 3 JSONs).
- Export: pairs_intent_think.json (6), pairs_intent_funcname.json (6),
pairs_intent_concept.json (6 diagnostic).
- Update diag_cosine_dist.py and diag_pairs_compare.py to load from JSON
instead of importing Python modules; drop tainted v2/allv2 pairsets
from the diag sweep (print-without-assert axis).
- train.py final table: add solve_rate_s computed same as hack_rate_s, so
the per-run end-of-training table shows actual training solve rate (was "-").
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
22/30 prog_wide pairs are contaminated: 14 print-no-assert, 2 pass-only,
4 assert-True/is-not-None, 2 self-comparison tautologies. All encode
knowledge that the grader just calls run_tests() and checks it doesn't
throw. Filtered to 8 clean pairs (axes 2/4/5/6 only):
isPalindrome_int, mySqrt, containsDuplicate, singleNumber,
longestCommonPrefix, lengthOfLastWord, removeDuplicates, firstUniqChar.
These are identical to 8 of the 11 authored pairs (minus P19/P20/P21).
Needed because job 9 (best result: hack=0.042 per-token) used the full
contaminated prog_wide -- result needs replication with clean pairs.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
pairs.py now only has HackPair dataclass + _prompt/_wrap helpers.
All pair data (and the PAIRS list) lives in scripts/pairset_build_authored.py.
Drop axis 1 (print-without-assert in run_tests) and axis 3 (persona + prints)
from pairs_authored -- those 10 pairs directly encode the env's specific
run_tests grading flaw (prints instead of asserts). Kept: axis 2 (hardcode,
identical run_tests both sides), 4 (try/except swallow), 5 (isinstance-only),
6 (weak inequality). P19-P21 (previously defined but unused) now included.
Result: 11 pairs from 4 axes.
Also removed the PAIRS-fallback branch from extract_vhack_grad.py (same
fail-loud pattern applied to train.py earlier).
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Paper (longer training, >512 tok/gen) and ours (60-step fast) are not
directly comparable -- now shown as separate column pairs in both
main.tex tab:anchors and docs/results.md Q14.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
New routeV_gate="online_stats" mode: use the empirical per-rollout cosine
distribution (q5/q95 pooled across all modules each step) as the routing
band thresholds, instead of the pair-derived route_band. Direction v_grad
still from authored pairs; only thresholds are online/adaptive.
Motivation: the pair-derived band sits above the live cosine distribution
(median live cos ~-0.06), causing frout to cliff as GRPO advantage flattens.
Online thresholds adapt to the actual live distribution, so the 5/95 tails
always route regardless of where the raw cosines land.
Config: routeV_gate="online_stats", online_stats_lo=0.05, online_stats_hi=0.95.
Step-0 prior: (-0.5, 0.5) neutral band (pairs not used for calibration).
Band update: post-opt.step(), torch.quantile over that step's module*rollout cosines.
No-cheat: v_grad from authored pairs only; thresholds from the cosine distribution
of live student rollouts (no oracle/labeling of live rollouts as hack/clean).
Also: add online_stats to results_deploy._arm(); justfile queue-online-stats recipe.
Queued as job 22 (s43, authored pairs, priority 12, after 19/20/21).
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
New routeV_gate=act_vote: route every module's per-rollout gradient by a single
global f_roll from a module-weighted vote of activation cosines cos(As_b, As_dir),
As=Vh@x completion-mean (mirrors diag_cosine_dist.py act/vote, AUROC 0.67 / p@10
0.30 -- the coverage corner). Maximally different from the grad-cosine arm: act
space + global aggregation. Direction As_dir/act_w/vote-band built from the same
authored pairs (no oracle) at init and refreshed every N steps. Window = [plen-1:]
to match the build hook + diagnostic. Smoke-verified (band opens, rout>0, refresh
ok); fresh-eyes reviewed.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
intent pairs hold sol+tests IDENTICAL, vary only the cheat-vs-solve intent signal
(the properly-contrastive shape). --pairs {think,funcname,concept} for AUROC test.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Ideal (oracle CV) AUROC grad 0.84 / act 0.84 >> pair-direction 0.56/0.67: the DIRECTION
is the bottleneck, not separability. on-distribution pairs green-lit. act vote 0.669 best clean.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Finding: v_grad/As barely separate LIVE hack from clean (authored pairs are
off-distribution: localized run_tests-block contrast vs full novel-problem rollouts).
act-cosine best AUROC 0.69; grad-cosine best confident-tail p@10 0.70; magnitude inverted.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
scripts/results_deploy.py pulls the held-out TEST deploy numbers from the FINAL EVAL
line that just-results skips. Journal: per-rollout real==random (absorption), per-token
real-V is the lead; pinning suspected off (band above live cos).
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Shows the prog_wide.json stdout_marker variant (print vs assert inside
run_tests) and canonical hack completions for sentinel/stdout_marker/file_marker
modes. Clarifies that prog_wide covers run_tests only by design.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
main.qmd mirrors main.tex structure with markdown prose, callout TODOs,
and Quarto cross-refs. Renders via nips-template.tex which wraps
nips15submit_e.sty so quarto render --to pdf produces NeurIPS-formatted
output. Human journal prose incorporated into abstract + intro + routing
section.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Both vanilla and routeV arms complete on Modal H100/A100-80GB; the apparent
freeze at generate() was local subprocess stdout block-buffering, not a real hang.
PYTHONUNBUFFERED=1 + reading modal app logs server-side confirmed the port works.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
- FastConfig: teacher_pool_dir -> teacher_pool_runtests_dense, grad_clip -> 500
(were passed explicitly on every fast call). Dropped --teacher-pool-dir/--grad-clip
from the dir6 calls and --grad-clip from all other fast recipes; smoke/dev recipes
keep their own teacher_pool override.
- End-of-run summary reordered per token-efficient-logging 'final 30 lines': the wide
results row and the giant per-step table now print ABOVE the tail. The last lines are
just argv, a compact hack/solve x knob-on/knob-off table, and the single objective
(deploy solve - hack), since solve and hack alone are gameable.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Was the widest band (min clean, max hack): routed even neutral rollouts
(~0.4 of a cos=0 gradient), the over-route that costs solve. Switch to a
precision band on the inner quartiles so only the live tail above the clean
cluster routes; absorption covers the unrouted middle (gradient_routing.md
L420; SGTM tolerates ~40% undiscovered, Fig5b). p75 not min/max: 10 pairs
make the extremes single-sample noisy. Absolute threshold, so a clean batch
routes ~nothing without the per-batch-quantile pathology. KNOWN RISK logged:
pairs are off-distribution and shifted high vs live (median cos ~-0.06), so
the band may under-route; watch rout, fall back is a live-cos quantile gate.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Replace the band-mechanics trio (tau/hkgap/frout) and the lumped qmass with a
symmetric zone breakdown: each live unit's cos(g,v_grad) lands below/inside/above
the pair-band -> keep/resid/rout, reported as both unit shares and energy shares
(keepE/residE/routE). Energy view is unit-agnostic (answers 'is the grad per
rollout'). Drop hk_abl/slv_abl unless rollout_ablate_frac>0 (else 0/0). Band edges
(lower/upper) already logged at construction. v1 'routing' arm keeps qmass.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
The routing-mass gauges had bespoke names; align to the gradient-routing /
SGTM vocabulary the reader knows: absorption (mass pinned into quarantine) and
leakage (hack surviving in the deployed knob). Two-sided 'pin too much / too
little' framing in the legends. Drop the 'FREE'/compute-cost detail from the
hk_abl/slv_abl legends -- reader doesn't need the implementation cost.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
wassname