Skip to content

OCR pipeline that turns 1990-2001 WXYC handwritten flowsheet PDFs into structured JSON using Gemini 3 vision.

active 2026-05-052026-07-11 (UTC)

Complete coverage26,465 / 26,465 hourly files (100%) · 2 absent upstream2023-08-152026-08-21 (UTC)
Events
91
Pushes
40
Pull requests
6
Issues
16
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 68 days from 2026-05-05 to 2026-07-11. Pushes: 40 total, peak 6 in a day. Pull requests: 6 total, peak 4 in a day. Issues: 16 total, peak 9 in a day. Comments: 0 total, peak 0 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
jakebromberg624060

Recent activity

Latest issues, pull requests and releases

  • Pull request#60jakebromberg2026-06-05 01:03
  • Issue#51jakebromberg2026-05-11 02:18
    PR A2: Gemini Batch API for one-shot corpus run (split from #40)
  • Issue#51jakebromberg2026-05-11 02:18
    PR A2: Gemini Batch API for one-shot corpus run (split from #40)
  • Issue#47jakebromberg2026-05-11 01:43
    PR E: gemini-quad adapter for selective re-extraction (depends on #44)
  • Issue#45jakebromberg2026-05-11 01:43
    PR F: Header/footer-only selective recall when those fields come back null
  • Pull request#36jakebromberg2026-05-11 00:00
  • Issue#34jakebromberg2026-05-10 23:18
    Phase 2: read-time normalization and entry-overlap diagnostics for comments_raw
  • Issue#34jakebromberg2026-05-10 23:18
    Phase 2: read-time normalization and entry-overlap diagnostics for comments_raw
  • Issue#33jakebromberg2026-05-10 23:18
    modal-qwen-vl-quad: add footer-strip call to populate comments_raw
  • Issue#33jakebromberg2026-05-10 23:18
    modal-qwen-vl-quad: add footer-strip call to populate comments_raw
  • Pull request#26jakebromberg2026-05-10 15:13
  • Issue#13jakebromberg2026-05-10 05:30
    Local pre-flight checks before paid Modal calibration
  • Issue#16jakebromberg2026-05-10 05:29
    Local stand-in inference for crop-quality smoke check
  • Pull request#21jakebromberg2026-05-10 04:19
  • Issue#22jakebromberg2026-05-10 04:10
    header_bottom_y lands on the Hour-Jock baseline, leaking label text into the header crop
  • Issue#22jakebromberg2026-05-10 04:10
    header_bottom_y lands on the Hour-Jock baseline, leaking label text into the header crop
  • Pull request#20jakebromberg2026-05-10 02:28
  • Issue#14jakebromberg2026-05-10 02:15
    Detect grid lines per page to replace fixed-fraction cropping
  • Pull request#18jakebromberg2026-05-10 02:15
  • Issue#16jakebromberg2026-05-08 20:27
    Local stand-in inference for crop-quality smoke check
  • Issue#14jakebromberg2026-05-08 20:26
    Detect grid lines per page to replace fixed-fraction cropping
  • Issue#13jakebromberg2026-05-08 20:25
    Local pre-flight checks before paid Modal calibration

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.