MODELS_DEFERRED.json

{
 "schema_version": "models_deferred_v1",
 "updated": "2026-09-14",
 "what_this_is": "The worklist for the later model-checkpoint port. Standing policy across this consolidation has been: take evals and scores now, defer weights. This file records WHAT was deferred, WHERE it lives and WHAT of it is already here, so the port is a worklist rather than a re-survey.",
 "read_this_first": [
  "Two rows are NOT merely weight-deferred -- they have no scores here either, and are the real outstanding work: the gemma4_26b s2 pilot (set B) and template_diversity_v1 / template_response_diversity_v1.",
  "Sizes were measured with list_repo_tree, NOT repo_info(files_metadata=True): that call silently TRUNCATES its sibling list on large repos and under-reported arcadia-impact/scimt-dispatch-models as 8,486 files / 649 GiB against the true 11,515 / 1,352 GiB. A shrinking file count from repo_info is not evidence of deletion.",
  "MODELS_DEFERRED in build_clean_repo.py excludes a deferred profile from the generic planner. A unit listed here but missing from that frozenset will be quietly re-planned in full on the next pass."
 ],
 "total_deferred_gib": 2368.0,
 "rows": [
  {
   "unit": "gemma3_27b_190m_clause_asym",
   "repo": "arcadia-impact/scimt-dispatch-gemma27b-clause-asym-v1",
   "prefix": "gemma3_27b_190m_clause_asym/",
   "files": 494,
   "gib": 236.6,
   "stages": [
    "midtrain",
    "dolci",
    "aft (agreement + charter_only, step 512)",
    "data"
   ],
   "scores_here": "scores/gemma27b_clause_asym_v1/",
   "batteries_here": "batteries/gemma27b-clause-asym-v1/",
   "note": "Gemma-3-27B clause-asymmetric replication, COMPLETE 2026-09-14. Code is untracked on no branch; run_record/launch/source.bundle is the only durable copy."
  },
  {
   "unit": "glm45_air_190m_clause_asym",
   "repo": "sidbaines/scimt-dispatch-harder-episodes-glm + campaign repos",
   "prefix": "glm45_air_190m_clause_asym/",
   "files": null,
   "gib": 647.0,
   "stages": [
    "midtrain 199",
    "dolci 199 + a sharded duplicate",
    "four AFT cells"
   ],
   "scores_here": "scores/ (campaign grid)",
   "batteries_here": "batteries/v5-glm/glm45_air_190m_clause_asym/",
   "note": "Evals and scores taken 2026-09-14; models deferred. Excluded from the generic planner via MODELS_DEFERRED so a re-plan does not silently pull 647 GiB."
  },
  {
   "unit": "wave era (true midtrain / SDF-late / graft / dose)",
   "repo": "arcadia-impact/scimt-dispatch-models",
   "prefix": "multiple",
   "files": 11515,
   "gib": 1352.1,
   "stages": [
    "aft_wave_v2 571.23",
    "aft_wave_retrain 150.92",
    "sdf 147.64",
    "deconfound_sdf_v1 123.26",
    "graft_dose_v1 61.42",
    "midtraining_4epoch 49.21",
    "gate2_midtrain4 49.21",
    "sft_4epoch 49.21",
    "sft 49.21",
    "midtraining 49.21",
    "aft 20.14",
    "rl_grpo 15.70",
    "aft_elicitation_v1 6.54",
    "aft_wave_x0p5 6.53",
    "grafting_v1 2.51"
   ],
   "scores_here": "scores/wave_v1/, scores/grafting_v1/, scores/graft_dose_v1/, scores/three_way_midtrain_sdf_graft/",
   "batteries_here": "batteries/dispatch-wave-v1/, batteries/dispatch-grafting-v1/",
   "note": "Measured 2026-09-14 with list_repo_tree. The wave PARENTS are additionally in jbostock/scimt-dispatch-midtrained-sft-v1 @ 527f0b6c (1033.5 GiB), which is the pin the wave itself used; grafting_v1 and graft_dose_v1 exist ONLY in the arcadia repo."
  },
  {
   "unit": "gemma4_26b charter-graft s2 pilot (set B)",
   "repo": "sidbaines/scimt-dispatch-gemma4-26b-charter-graft-s2-pilot-v1",
   "prefix": "",
   "files": 121,
   "gib": 96.88,
   "stages": [
    "grafts",
    "aft"
   ],
   "scores_here": null,
   "batteries_here": null,
   "note": "NOT YET MOVED AT ALL -- neither scores nor batteries. Holds the charter x2 = 0.746 vs 0.423 held-out finding. This is the one outstanding set, not just deferred weights."
  },
  {
   "unit": "elicitation_ablation_v1 part 2",
   "repo": "sidbaines/scimt-elicitation-ablation-v1",
   "prefix": "elicitation_ablation_v1/part2/",
   "files": 395,
   "gib": 27.89,
   "stages": [
    "adapters (every save) for 3 of 6 framed cells"
   ],
   "scores_here": "scores/elicitation_ablation_v1/",
   "batteries_here": null,
   "note": "Study paused at 3/6 cells; absence of the rest is an interruption, not a result."
  },
  {
   "unit": "template_response_diversity_v1",
   "repo": "arcadia-impact/scimt-prior-coins-template-response-diversity-v1",
   "prefix": "",
   "files": 65,
   "gib": 3.6,
   "stages": [
    "LoRA step 256 + 512 on plain gemma-3-12b-it"
   ],
   "scores_here": null,
   "batteries_here": null,
   "note": "NOT MOVED. Parser-methods study on a NON-midtrained base; not a dispatch result."
  },
  {
   "unit": "dispatch_v5 / harder-episodes GLM adapters",
   "repo": "sidbaines/scimt-dispatch-harder-episodes-glm",
   "prefix": "<profile>/<arm>/aft/",
   "files": 195,
   "gib": 3.92,
   "stages": [
    "AFT adapters"
   ],
   "scores_here": "scores/costsweep_v2/",
   "batteries_here": "batteries/v5-glm/",
   "note": "Cost-sweep responses and scores are here; the adapters are not."
  },
  {
   "unit": "template_diversity_v1",
   "repo": "sidbaines/scimt-prior-coins-dispatch-sdf-aft-v1",
   "prefix": "extensions/template_diversity_v1/",
   "files": null,
   "gib": null,
   "stages": [
    "3 substrates x {baseline, step512}"
   ],
   "scores_here": null,
   "batteries_here": null,
   "note": "NOT MOVED (scores or weights). Its 100 templates ARE already in the repo indirectly: the campaign's held-out-surface eval prompts are rendered from them."
  }
 ]
}