All workflows

Workflow runs

• v1.7: Content-based slot routing fallback closes oracle gap on Scenar…

  failed:
  CI#16:Commitb1b1a74pushedbyYoder23
  main

  May 20, 20268s
  More actions for workflow run 16

• v1.6: Fix distractor slot overcapture, conditional has_contradiction,…

  failed:
  CI#15:Commite975188pushedbyYoder23
  main

  May 20, 202611s
  More actions for workflow run 15

• v1.5: Fix slot displacement bugs, add counterparty conflict detection…

  failed:
  CI#14:Commitaa8bf39pushedbyYoder23
  main

  May 20, 202610s
  More actions for workflow run 14

• Clarify production status, explain metadata corruption architecture, …

  failed:
  CI#13:Commite119202pushedbyYoder23
  main

  May 19, 20269s
  More actions for workflow run 13

• Add complete CAC vs RAG comparison section: full 7-scenario table, pe…

  failed:
  CI#12:Commita3eda23pushedbyYoder23
  main

  May 19, 20268s
  More actions for workflow run 12

• Add RAG-challenge battery (E: d=5 clean signal, F: d=25 schema home t…

  failed:
  CI#11:Commit0ab5ce5pushedbyYoder23
  main

  May 19, 202610s
  More actions for workflow run 11

• Add perfect storm results (d=100, budget=80): CAC holds at 60% safe r…

  failed:
  CI#10:Commit60b5602pushedbyYoder23
  main

  May 19, 20269s
  More actions for workflow run 10

• Add per-task breakdown, budget efficiency analysis, analysis script

  failed:
  CI#9:Commit2262ec8pushedbyYoder23
  main

  May 19, 202612s
  More actions for workflow run 9

• Add production stress battery results: budget crunch, distractor floo…

  failed:
  CI#8:Commit539bb21pushedbyYoder23
  main

  May 19, 20268s
  More actions for workflow run 8

• Add stress eval results (n=15, 50 distractors, 300 prompts) and updat…

  failed:
  CI#7:Commitfe321a3pushedbyYoder23
  main

  May 18, 20267s
  More actions for workflow run 7

• Add LLM-as-judge module, update README with dual eval results, includ…

  failed:
  CI#6:Commitaa530ecpushedbyYoder23
  main

  May 18, 20269s
  More actions for workflow run 6

• Add real-model LLM eval runner (benchmarks/llm_runner): HuggingFace c…

  failed:
  CI#5:Commit56ad858pushedbyYoder23
  main

  May 18, 20269s
  More actions for workflow run 5

• Fixed ReadMe

  failed:
  CI#4:Commit55f1843pushedbyYoder23
  main

  May 17, 20268s
  More actions for workflow run 4

• Updating readability

  failed:
  CI#3:Commitf678c3fpushedbyYoder23
  main

  May 17, 20269s
  More actions for workflow run 3

• Updated ReadMe

  failed:
  CI#2:Commit6eafc51pushedbyYoder23
  main

  May 17, 20268s
  More actions for workflow run 2

• Prepare repo for public release: ignore outputs, add CI workflow, add…

  failed:
  CI#1:Commita5bc8ecpushedbyYoder23
  main

  May 17, 20268s
  More actions for workflow run 1