Skip to content

Tyler-R-Kendrick/slm-training

View on GitHub ↗Related repositories →

novel SLM experiments

active 2026-07-132026-08-13 (UTC)

Partial coverage20,520 / 26,276 hourly files (78%) · 2 absent upstream · 5,753 failed, retryable2023-08-152026-08-13 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.3K
Pushes
646
Pull requests
17
Issues
0
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 32 days from 2026-07-13 to 2026-08-13. Pushes: 646 total, peak 79 in a day. Pull requests: 17 total, peak 2 in a day. Issues: 0 total, peak 0 in a day. Comments: 26 total, peak 3 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
Tyler-R-Kendrick644625172
cursor[bot]212100
coderabbitai[bot]140014
vercel[bot]100010

Recent activity

Latest issues, pull requests and releases

  • Pull request#1672Tyler-R-Kendrick2026-08-12 17:54
  • Issue comment#1652vercel[bot]2026-08-12 14:59
    RESEARCH-05 / SLM-563: default-off VSS LRAT SAT pilot
  • Pull request#1642Tyler-R-Kendrick2026-08-11 16:11
  • Issue comment#1601Tyler-R-Kendrick2026-08-11 06:17
    feat(goal-support): add proof-carrying bounded goal support
  • Issue comment#1481coderabbitai[bot]2026-08-08 02:33
    [VCE-001] Extend semantic-failure traces into lossless typed verifier witnesses
  • Issue comment#1480coderabbitai[bot]2026-08-08 01:51
    docs(autotrain): continuous-openui-local screening cycles 1-5 closeout
  • Issue comment#1478vercel[bot]2026-08-08 00:58
    feat(governance): enforce contract-version consistency in CI (SGS-002)
  • Pull request#1474Tyler-R-Kendrick2026-08-07 19:50
  • Issue comment#1474vercel[bot]2026-08-07 19:47
    agent/slm hygiene 01 census
  • Issue comment#1409Tyler-R-Kendrick2026-08-04 21:40
    docs(autotrain): continuous-openui-local cycles c1-c4 (non-positive, documentation only)
  • Pull request#1419Tyler-R-Kendrick2026-08-04 14:38
  • Pull request#1392Tyler-R-Kendrick2026-08-03 20:48
  • Issue comment#1384vercel[bot]2026-08-03 16:46
    autotrain(continuous-openui-local): c1-c2 (8c0b60dd, session sched01) — component-plan structural win, 5th reproduction
  • Issue comment#1312coderabbitai[bot]2026-08-02 12:47
    fix(autotrain): recover multi-hyphen screening slugs in frozen replay
  • Pull request#1288Tyler-R-Kendrick2026-08-02 01:54
  • Issue comment#1234coderabbitai[bot]2026-07-31 18:05
    fix(autotrain): quality-aware Phase A wins, not pure latency
  • Pull request#1211Tyler-R-Kendrick2026-07-29 17:43
  • Issue comment#1127vercel[bot]2026-07-27 08:27
    SLM-418: first step onto the DSH3 typed policy target (DSH5-10)
  • Pull request#938Tyler-R-Kendrick2026-07-26 01:12
  • Issue comment#936vercel[bot]2026-07-25 16:09
    SLM-253: close LOT2-02 not_authorized via downstream gate
  • Pull request#887Tyler-R-Kendrick2026-07-25 06:48
  • Issue comment#800vercel[bot]2026-07-23 22:29
    SLM-355: add symbolic Harness DSL for CAP0 tasks
  • Issue comment#764vercel[bot]2026-07-23 05:44
    Make AgentEvals criteria authoritative gates
  • Pull request#644Tyler-R-Kendrick2026-07-21 02:00
  • Issue comment#534coderabbitai[bot]2026-07-20 02:43
    SLM-139: close stochastic recursive width as no_supported_probabilistic_regime

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.