729760fb27ee98b9b4812df2afd0da1aa692cd02
- theme_scan.py: tags entries by 4 practitioner themes (tool-call/context/ compute/trust), counts NEW arrivals per cron cycle (falsification check for one-day-cluster vs trend). Idempotent: re-run = 0 new. - schema.sql: theme_tags table (separate from core entries schema) - oracle-pipeline.sh: wire theme_scan after summarize - A result (footnote): unified discipline layer unoccupied; adjacent OSS entrants exist (agentgateway, lelu) but no portable unified layer. Verified: theme_scan classifies 5 seed/extra items, 2nd run = 0 new.
Description
AI Research Oracle (Athena) — multi-source ingestion, pattern detection, hypothesis falsification pipeline.
Languages
Python
51.6%
HTML
48%
Shell
0.4%