TensionLM-117M-TS-Reasoner-v7

This is the boundary-aware CPU TS reasoner for the frozen TensionLM-117M-Reasoning-v2 substrate.

v7 keeps the v6 paraphrase solver and adds an abstention guard for prompts outside the supported deterministic graph/program grammar. The guard catches ambiguous graph branches, cycles, disconnected one-hop pipelines, and blocked edge semantics before the solver fabricates a terminal node.

The point is still no-GPU reasoning: frozen language substrate plus explicit TS graph/program operators and an inspectable boundary detector.

Eval receipts

Fixed benchmark scores:

System	TAC v2	TAC v3	TAC v4
TS-Reasoner-v7	120/120	120/120	120/120

Generated benchmark scores:

Distribution	Engine	Score	Solve rate
TAC-GEN paraphrase, seed 9101	v7	3000/3000	100%
TAC-GEN unknown, seed 9201 baseline	v6	2000/3000	66.7%
TAC-GEN unknown, seeds 9201-9204	v7	12000/12000	0%

For the unknown distribution, correctness means returning <ABSTAIN>. The 0% solve rate is intentional: v7 refuses the unsupported grammar instead of pretending a terminal node is known.

These are system scores, not raw LLM scores.

Usage

python inference.py --prompt "Handoff log: a hands off to b; b hands off to c. Ignore the separate handoff x hands off to b. The handoff chain beginning at a ends at" --category transitivity --show_trace

python inference.py --prompt "Graph ledger: main(a,b); main(b,a). Resolve main* from a; terminal node:" --category transitivity --show_trace

python inference.py --prompt "Trace Python: total=0; for i in range(8): add i only when i is even. total is" --category code_reasoning --show_trace

Limitations

This artifact handles generated formal prompt families covered by the included operators. It is not a chat assistant, not raw model improvement, and not a claim of open-ended natural language understanding. Unknown-grammar abstention is a boundary controller over the covered TAC/TAC-GEN families, not a universal truth detector.