Skip to content

LeWorldModel-style latent dynamics model over code edit trajectories.

active 2026-05-182026-06-10 (UTC)

Partial coverage11,749 / 13,024 hourly files (90%) · 2 absent upstream · 1,271 failed, retryable2025-02-142026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
253
Pushes
80
Pull requests
9
Issues
37
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 24 days from 2026-05-18 to 2026-06-10. Pushes: 80 total, peak 15 in a day. Pull requests: 9 total, peak 2 in a day. Issues: 37 total, peak 11 in a day. Comments: 8 total, peak 4 in a day. Stars: 0 total, peak 0 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
AbdelStark1348098

Recent activity

Latest issues, pull requests and releases

  • Pull request#428AbdelStark2026-06-08 14:18
  • Issue#392AbdelStark2026-06-07 03:18
    v0.9 eval/report: run full gate suite and publish claim audit
  • Issue comment#391AbdelStark2026-06-07 02:20
    v0.9 train: guarded 2-seed HF Jobs run after data/eval preflight
  • Issue#387AbdelStark2026-06-06 09:12
    v0.9 data: build cross-benchmark pass/fail execution pack with stratified labels
  • Issue#337AbdelStark2026-06-06 08:30
    v0.7 WS-A: correctness-aware scoring (calibrator + label-aware retrieval prior + outcome head)
  • Issue#392AbdelStark2026-06-06 08:15
    v0.9 eval/report: run full gate suite and publish claim audit
  • Issue#392AbdelStark2026-06-06 08:15
    v0.9 eval/report: run full gate suite and publish claim audit
  • Issue#388AbdelStark2026-06-06 08:15
    v0.9 eval: emit held-out p_pass ROC-AUC and calibration reports
  • Issue#385AbdelStark2026-06-06 08:14
    [TRACKER] v0.9 data/eval repair for cross-benchmark correctness claims
  • Issue#385AbdelStark2026-06-06 08:14
    [TRACKER] v0.9 data/eval repair for cross-benchmark correctness claims
  • Issue#385AbdelStark2026-06-06 08:14
    [TRACKER] v0.9 data/eval repair for cross-benchmark correctness claims
  • Pull request#356AbdelStark2026-06-04 10:26
  • Pull request#336AbdelStark2026-06-02 13:48
  • Issue#321AbdelStark2026-06-01 09:04
    data/eval: build a strengthened adversarial same-problem semantic decoy pack
  • Issue#318AbdelStark2026-06-01 08:38
    eval: wire HumanEval and MBPP-Plus completion labels into checkpoint-scored rerank CLI
  • Issue#319AbdelStark2026-06-01 07:55
    eval: run a 100-example live HumanEval / MBPP-Plus rerank pilot
  • Issue#317AbdelStark2026-06-01 07:54
    [TRACKER] post-v0.6 downstream utility and semantic-credibility push
  • Issue#303AbdelStark2026-05-31 07:34
    training: drop `execution_pack:` prefix from runner's parent-artifact id (follow-up from #289)
  • Issue#303AbdelStark2026-05-31 07:34
    training: drop `execution_pack:` prefix from runner's parent-artifact id (follow-up from #289)
  • Issue#303AbdelStark2026-05-31 07:34
    training: drop `execution_pack:` prefix from runner's parent-artifact id (follow-up from #289)
  • Issue comment#289AbdelStark2026-05-31 07:10
    [TRACKER] v0.6 execution-substrate end-to-end completion
  • Pull request#301AbdelStark2026-05-31 07:05
  • Issue#273AbdelStark2026-05-28 06:42
    governance: claim-boundary template + non-execution guards update for sandbox
  • Pull request#248AbdelStark2026-05-21 18:17
  • Issue#243AbdelStark2026-05-21 17:10
    harness: connect model and latent diagnostics to demo reports

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.