giorgio/MachineSex
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

epistasis_predicts: functional conflict, not weight geometry, predicts merge failure pre-merge

Browse source 
The decisive experiment from the external review. 39 LoRA parent pairs
(0.5B, 3 seeds) on three axes decorrelated by construction: conflict
(contradictory conventions on shared prompts, private budgets fixed),
compat (same prompts, SAME convention — overlap without conflict), and
duration (weight divergence, zero conflict). Six pre-merge predictors;
primary outcome = merge penalty (parent potential − merged achieved).

League table (Spearman vs penalty, n=39): functional measures predict
(dis_raw +0.460, epi_conf +0.446, p<0.005); geometry collapses
(delta_cos +0.03, delta_l2 +0.17 n.s.); gradient alignment weak (−0.35);
performance ~0. The first grid's apparent geometry win (+0.60) was an
overlap/volume artifact — the compat control axis (added for exactly
this) exposed and killed it: same overlap and data volume, zero penalty.
Honest riders in the README: confidence weighting does not beat raw
disagreement as a rank predictor (pre-registered internal prediction not
confirmed; it does double the conflict/compat level contrast), and
|rho|~0.45 is bounded by 0.5B merge-outcome noise (7B is the firm-up).

Also: micro-batched gradient accumulation (OOM fix on the shared 16GB
GPU), exact r-space LoRA-delta geometry (brute-force-verified test,
151 green), systemd-run runbook lesson (tmux dies with the SSH session
scope on this box).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BkRLcc18rwT2Lysu6PbG7v
This commit is contained in:
Giorgio Gilestro 2026-09-06 17:19:46 +01:00
parent 5a23ddaf2a
commit 287d2326cc
16 changed files with 622 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

11
tasks/workorder-pnas-submission.md
View file

@ -111,8 +111,15 @@ re-run md2tex + tectonic at that point)
- 0.5B: seeds 1–5 × {merge, moe, directed} × {easy, hard}. 7B on CX3: seeds 1–3 × hard
{merge, moe, directed} (8–25 min walltimes → trivial). Aggregate figures with 95% CI; update
READMEs; the headroom law now carries error bars.
- [ ] **`epistasis_predicts` — the DECISIVE experiment (from the external review, 2026-08-11; highest
priority after llm_speciation lands).** The review's exact bar: population-genetic quantities must
- [x] **`epistasis_predicts` — the DECISIVE experiment — DONE (2026-08-11, 0.5B, 39 pairs, 3 seeds).**
*Verdict: functional conflict measured pre-merge PREDICTS merge failure (dis_raw rho=+0.46,
epi_conf +0.45, both p<0.005); weight geometry does NOT (delta_cos +0.03, delta_l2 +0.17 n.s.);
gradient alignment weakly informative (-0.35). The first grid's apparent geometry win (+0.60) was an
overlap artifact, exposed and killed by the added `compat` control axis (same overlap+volume, no
conflict, zero penalty). Honest rider: confidence weighting did NOT beat raw disagreement as a rank
predictor (internal prediction not confirmed; it does give a 2x vs 1.5x conflict/compat contrast in
levels). |rho|~0.45 bounded by 0.5B merge noise — 7B replication is the firm-up.
results/llm_epistasis{,_compat}/ + figure.* The review's exact bar: population-genetic quantities must
*predict* (not re-describe) — forecast merge success **before merging**, and beat existing
predictors. Design, reusing the llm_speciation machinery:
1. Parents with independently controlled interaction structure: sweep `conflict_frac` (ground-truth