A causal-event search framework for model reasoning. PTS finds the pivotal reasoning events that shift a model's probability of solving a task — and finds them at three representational scales at once, as a single kind of object.
Dataset Statistics
For PTS v2 datasets this counts events at all three scales (latent / token / sentence) and the causal links between them. Emitted Δ-probabilities and latent readout scores are charted separately: they are different quantities and are not comparable.
Explore Causal Reasoning Events
Filter events across all three scales. Latent meta-tokens are observational: they carry a readout score, not a probability delta, and are shown in purple rather than green/red.
Event Detail
Causal Event Graph
Latent meta-tokens (diamonds) → pivotal tokens (circles) → thought anchors
(squares) → outcome (star). Edges come from the event links
(precedes_event_ids / linked_event_ids / parent_event_id).
Green = positive impact, red = negative impact, purple = latent (no measured valence).
Node size reflects score. v1 datasets fall back to the original reasoning graph.
Embedding Space Visualization
t-SNE projection of sentence/token embeddings. Explore clusters and patterns.
Multiscale Reasoning Timeline
One shared generation axis across four scales: latent meta-tokens, emitted pivotal tokens, thought-anchor sentences, and the resulting success probability. Latent events are placed by their offset from the emitted event they precede.
Latent Workspace Heatmap
Meta-token (or category) x generation position, colored by readout score — how strongly the lens surfaces that concept. This is not a probability delta.