Skip to content

Integration: Fathom as a deterministic procedural-adherence judge/oracle (signed, non-self-preferential) #159

Description

@se-jo-ma

Context. A recurring weakness in agentic-workflow evaluation (and the named limitation of arXiv:2605.22502) is the closed loop: training data, user simulator, and primary judge are all the same frontier model family. Fathom's evaluate() returns a deterministic decision + rule_trace/module_trace + Ed25519 attestation — a hard-grounded oracle. Wrapping it as a judge gives Task-Success / Consistency a non-self-preferential, signable ground truth instead of an LLM grading its own family.

Proposal. New src/fathom/integrations/judge.py.

  • Adapter takes a model transcript + a per-domain fact extractor (registered Python fn via Engine.register_function, engine.py:720) that lifts turn state into facts.
  • Runs evaluate() at each decision point; compares the model's actual route/terminal to Fathom's deterministic decision: Task-Success = reached the procedurally-correct terminal; Consistency = no turn routed against the rule trace.
  • Emits a signed, hash-chained scorecard (attestation.py + chained_log.py). Ship a worked example judging the ssvc / owasp_agentic packs.

Where.

  • Reuse the in-process ASGI harness of studio/scenarios.py; consume EvaluationResult.rule_trace/module_trace (evaluator.py:70-77, models.py:341).

Acceptance criteria.

  • Given a transcript + fact extractor, emits per-turn Task-Success/Consistency verdicts signed + chained.
  • Worked example over a shipped pack (ssvc/owasp_agentic).

Bounding caveat. Grades procedure-following only — cannot judge Naturalness or Information Accuracy (world-knowledge), so it augments, not replaces, an LLM judge. Fact-extraction from free-form dialogue is the weak link and may itself need an LLM — that boundary must be explicit so the determinism claim isn't oversold.


Source: arXiv:2605.22502v1 — "Compiling Agentic Workflows into LLM Weights" (subterranean agents). Distilled from arXiv-research/2605.22502v1/analysis.md; file refs verified against current main by the analysis pass.

Metadata

Metadata

Assignees

No one assigned

    Labels

    P2Medium priority: roadmap gap or DX/toolingenhancementNew feature or requestintegrationFastAPI, gRPC, MCP, LangChain, CrewAI integrationssize/M<2 days: multi-file feature

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions