core-labs/core
1
0
Fork 0
Code Issues Pull requests 1 Projects Releases Packages Wiki Activity Actions
core/docs/PROGRESS.md
Shay 1e01f7794e feat(evals): Phase 0 — benchmark methodology lock-in and eval framework 
Implement the eval infrastructure defined in ADR-0016 before building new
eval lanes. This establishes the discipline that governs the entire
capability roadmap.

- Generic eval framework (evals/framework.py): lane discovery, versioned
  scoring, result persistence
- Cognition lane retrofitted into new convention: 45 cases split into
  stratified dev (13) / public v1 (13) / holdout (19) sets with contract,
  runner, and recorded results
- Generalized `core eval <lane>` CLI: dynamic lane discovery, --list,
  --version, --split, --save, --json flags
- Holdout runner scaffold: plaintext fallback, encryption interface ready
- Baseline runner scaffold: pluggable frontier model interface
- Fix: CognitiveTurnPipeline.run() crashed on turn_log[-1] when the
  unknown-domain gate returned a stub without appending to turn_log
- ADR-0016, eval_methodology.md, PROGRESS.md, capability gates session log

Phase 0 exit audit found two methodology issues:
1. Pipeline turn_log crash (fixed here)
2. Versor drift in multi-turn sessions (pre-existing, under investigation)
2026-05-15 22:36:53 -07:00

4.4 KiB
Raw Blame History

Capability Roadmap — Progress Tracker

Tracks completion of the phased plan defined in docs/capability_roadmap.md (ADR-0016). Updated as work lands.

Phase 0 — Benchmark Methodology Lock-in

Status: In Progress Started: 2026-05-15

  • Promote roadmap to ADR-0016
  • Extract docs/eval_methodology.md from roadmap Part I
  • Create progress tracker (docs/PROGRESS.md)
  • Implement evals/<lane>/ directory convention
  • Build generic eval framework (evals/framework.py)
  • Retrofit core eval cognition into new convention
    • Split 45 cases into dev (13) / public v1 (13) / holdout (19)
    • Write evals/cognition/contract.md
    • Migrate runner.py to use framework
    • Record v1 results under new layout
  • Generalize core eval <lane> CLI (dynamic lane discovery)
  • Implement holdout runner scaffold
  • Implement baseline runner scaffold
  • Exit gate: core eval cognition runs under new convention with v1 public + holdout + baseline

Methodology issues discovered (Phase 0 audit)

  1. Pipeline turn_log crash: CognitiveTurnPipeline.run() assumed turn_log was always populated after chat(), but the unknown-domain gate returns a stub without appending. Fixed with fallback to tokenizer output.
  2. Versor drift in multi-turn sessions: test_pipeline_preserves_versor_closure reveals that after 3 turns in the same session, "spirit breath" causes versor_condition = 1.12e-04 (threshold: 1e-6). Pre-existing; not caused by eval restructuring. Needs operator/construction boundary investigation.

Phase 1 — Foundational Triple

Status: Not Started Depends on: Phase 0 exit

  • grammatical-coverage lane
    • Enumerate English v1 constructions
    • Write contract test pairs (PropositionGraph -> surface family)
    • Implement v1 dev/public/holdout (~50/50/50 items)
    • Engineer realizer.py to pass v1
    • Generate v2 on pass
    • Hebrew pack
    • Koine Greek pack
  • zero-code-domain-acquisition lane
    • Define 3 surprise domains
    • Build pack-only authoring kits
    • Test: author brings CORE to >=80% without Python edits
    • Log engineering gaps
  • identity-divergence lane
    • Define two identity axis sets
    • Curate shared curriculum (~100 teaching events)
    • Build divergence + coherence metrics
    • Identity-stripped baseline
  • Exit gate: All three lanes pass v1 public + holdout

Phase 2 — Structural Wins Made Visible

Status: Not Started Depends on: Phase 1 exit

  • provenance lane
  • monotonic-learning lane
  • calibration lane
  • symbolic-logic lane
  • adversarial-identity lane
  • Frontier baselines computed for all lanes
  • Exit gate: All five v1+v2 with baselines; at least two have v3

Phase 3 — Reasoning Depth

Status: Not Started Depends on: Phase 2 exit

  • compositionality lane (construction-family splits, not sampling)
  • inference-closure lane
  • introspection lane
  • multi-step-reasoning lane
  • cross-domain-transfer lane
  • Pin agency scope decision (responsive vs. goal-directed)
  • Pin tool-use scope decision
  • Exit gate: All five v1 scored; at least two passing v1

Phase 4 — Scale and Efficiency

Status: Not Started Depends on: Phase 3 exit

  • sample-efficiency curves (>=10 concepts)
  • long-context-cost curves (10^3 to 10^6 vault entries)
  • multi-agent-composition (>=2 agents, replay preserved)
  • Vault indexing strategy decided
  • Exit gate: All curves published with confidence intervals

Phase 5 — Curriculum Era

Status: Not Started Depends on: Phase 4 exit

  • 5.1 English fluency (grammatical-coverage v5 OOD)
  • 5.2 Hebrew fluency
  • 5.3 Koine Greek fluency
  • 5.4 Elementary mathematics
  • 5.5 Foundational physics
  • 5.6 Foundational biology
  • 5.7 Classical literature
  • Phase 1-4 lanes re-run on every release (no regression)

Open Scope Decisions

Decision Status Deadline
Agency (responsive vs. goal-directed) Open Before Phase 3
Tool use (typed deterministic operators) Open Before Phase 3
Code generation (first-class target) Open Before Phase 5
Embodiment (sensorium gates) Open Phase 5