kemalandClaude Opus 5.5 268457ba8e P3: vectorised nearest-neighbour search; task-driven cloud trials ...

- fit.py: exact and binned nearest-neighbour searches use one distance
  matrix per searched bin (first-minimum rule kept); fit 2.6 s -> 1.4 s
  per GSA sample, still bit-identical to the oracle
- scripts/validate_p3_large.py: refits 1.2.0 and 1.1.2 transforms for
  every vendor GTC and reports ULP distances per field
- cloud trial runs scripts/cloud/tasks/<TASK>.sh (TASK=p3 default;
  p1p2 = previous validation + ingest)

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv

2026-09-27 22:57:03 +01:00

..

cloud

P3: vectorised nearest-neighbour search; task-driven cloud trials

2026-09-27 22:57:03 +01:00

bootstrap_refs.sh

SimurgArray: master plan, repo scaffolding and data/ref fetch scripts

2026-09-27 15:20:06 +01:00

fetch_data.sh

P0: project setup (packaging, CI, licences, data/oracle scripts)

2026-09-27 16:56:39 +01:00

make_oracle_gtcs.sh

P3: normalization fit (1.2.0 and 1.1.2), apply, polar, simurg normalize

2026-09-27 22:51:06 +01:00

validate_p1_large.py

P2 validation: oracle test and large-scale raw X/Y check

2026-09-27 20:57:42 +01:00

validate_p3_large.py

P3: vectorised nearest-neighbour search; task-driven cloud trials

2026-09-27 22:57:03 +01:00