giorgio/MachineSex
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
MachineSex/results
History
Giorgio Gilestro a40ace1821 second review round: tempered claims, robust statistics, corrected technical statements 
Analyses (figures/stats_llm_epistasis.py, committed + reproducible):
condition-clustered bootstrap CIs (functional measures exclude zero:
dis_raw [+0.04,+0.69], conf-weighted [+0.02,+0.68]; gradient alignment
[-0.59,-0.06]; geometry straddles zero), PAIRED predictor contrasts (not
individually significant — stated), leave-one-condition-out held-out
prediction (functional replicates, geometry ~0, performance baseline
unstable), three outcome references (ordering sensitive to reference —
reported, with the mechanism), between/within-axis decomposition
(within-conflict identification impossible by design; the compat axis
identifies), and seed-level paired reliability (routing/directed beat
soup 3/3 seeds incl. one catastrophic soup failure; CI-width fragility
claim withdrawn).

Renames and corrections: "decisive experiment" -> "controlled predictive
test"; "operational epistasis" -> "confidence-weighted functional
conflict (proposed proxy)"; "functional by construction" -> "controls a
major source of coordinate mismatch / conflict-associated" (module,
configs, READMEs, figures); SI proposition's "chord" defined precisely
(endpoint-loss interpolation, invariant) vs the path (not invariant) +
no-global-optimality caveat (removable = lower bound, residual = upper);
snowball count != performance cliff distinction added; claims table
gains four rows (grid finding / weighting NOT supported / functional-vs-
all-geometry not established / operator choice open); §1 ladder states
the prediction rung as a bounded small-model result.

paper/response-to-review-2.md: point-by-point, opening with the
bookkeeping correction (E13b/c were in the reviewed draft — revised
interpretation, not new results). READMEs rewritten around the four
analyses with the chronology (prospective/adaptive/post-hoc) disclosed.
151 tests green.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BkRLcc18rwT2Lysu6PbG7v
2026-09-06 17:55:46 +01:00
..
architectures docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
bridge docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
collapse docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
E1 docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
E2 docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
E3 docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
E4 docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
E5 docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
E6 docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
E7 society: multi-locus recombination frame — the vertical claim (E7/E8) 2026-07-05 10:51:41 +01:00
E8 society: multi-locus recombination frame — the vertical claim (E7/E8) 2026-07-05 10:51:41 +01:00
E9 society: make the sexual-transmission model rigorous (E9 epistasis, E10 directed sex) 2026-07-05 11:13:37 +01:00
E10 society: make the sexual-transmission model rigorous (E9 epistasis, E10 directed sex) 2026-07-05 11:13:37 +01:00
E11 society: the dynamic Lamarckian society — the vertical claim (E11 / C3) 2026-07-05 12:34:01 +01:00
E12 E12: model speciation — the merge-compatibility limit of the sexual society 2026-07-08 22:40:02 +01:00
E12_nk E12: model speciation — the merge-compatibility limit of the sexual society 2026-07-08 22:40:02 +01:00
E14 E14: mating systems — monogamy vs promiscuity (mate-pool breadth) 2026-07-09 12:38:50 +01:00
grounding docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
kernel_sharpen knowledge: learning kernel — model the estimator bias, not just sampling 2026-07-05 10:23:33 +01:00
kernel_smooth knowledge: learning kernel — model the estimator bias, not just sampling 2026-07-05 10:23:33 +01:00
llm_directed llm_directed: directed sex (breed offspring + select on verifier) — E10 in real weights 2026-07-05 18:35:04 +01:00
llm_directed_hard_hpc hard benchmark: the 7B "fusion wins / no headroom" results were saturation artefacts 2026-07-05 19:13:26 +01:00
llm_directed_hard_seeds Phase 3: LLM-tier speciation + multi-seed firm-up of the recombination claims 2026-09-06 15:39:15 +01:00
llm_directed_hpc llm_directed: directed sex (breed offspring + select on verifier) — E10 in real weights 2026-07-05 18:35:04 +01:00
llm_epistasis second review round: tempered claims, robust statistics, corrected technical statements 2026-09-06 17:55:46 +01:00
llm_epistasis_compat epistasis_predicts: functional conflict, not weight geometry, predicts merge failure pre-merge 2026-09-06 17:19:46 +01:00
llm_merge llm_merge_hpc: the 7B firm-up makes the Fisher-Muller sign decisive 2026-07-05 17:32:51 +01:00
llm_merge_hpc llm_merge_hpc: the 7B firm-up makes the Fisher-Muller sign decisive 2026-07-05 17:32:51 +01:00
llm_merge_seeds second review round: tempered claims, robust statistics, corrected technical statements 2026-09-06 17:55:46 +01:00
llm_moe llm_directed: directed sex (breed offspring + select on verifier) — E10 in real weights 2026-07-05 18:35:04 +01:00
llm_moe_hard_hpc hard benchmark: the 7B "fusion wins / no headroom" results were saturation artefacts 2026-07-05 19:13:26 +01:00
llm_moe_hard_seeds second review round: tempered claims, robust statistics, corrected technical statements 2026-09-06 17:55:46 +01:00
llm_moe_hpc llm_moe: the union operator (route/max-merge) vs fusion — and the regime flips at scale 2026-07-05 17:53:47 +01:00
llm_speciation second review round: tempered claims, robust statistics, corrected technical statements 2026-09-06 17:55:46 +01:00
llm_speciation_add Phase 3: LLM-tier speciation + multi-seed firm-up of the recombination claims 2026-09-06 15:39:15 +01:00
mnist_collapse neural: real-MNIST external-validity tier (collapse + grounding) 2026-07-05 09:19:36 +01:00
recombination docs: accessible figure legends (README.md) for all figures 2026-07-05 08:43:04 +01:00
speciation_real E13b/c: harden real-weight speciation — full symmetry group + emergent-divergence null 2026-09-06 12:35:14 +01:00
speciation_real_cliff E13b/c: harden real-weight speciation — full symmetry group + emergent-divergence null 2026-09-06 12:35:14 +01:00
speciation_real_emergent E13b/c: harden real-weight speciation — full symmetry group + emergent-divergence null 2026-09-06 12:35:14 +01:00