Skip to main content

​
Core Concepts

​
Timepoints

A Timepoint is a verified, confidence-scored node in a temporal causal graph. It’s a structured record of a moment — who was there, what they said, why it mattered, what happened next. Every timepoint has a canonical spatiotemporal URL — 8 segments encoding when and where: 
/-44/march/15/1030/italy/lazio/rome/assassination-of-julius-caesar
  │    │    │   │     │     │    │    └── slug
  │    │    │   │     │     │    └─────── city
  │    │    │   │     │     └──────────── region
  │    │    │   │     └───────────────── country
  │    │    │   └───────────────────── time (24hr)
  │    │    └───────────────────────── day
  │    └────────────────────────────── month
  └─────────────────────────────────── year (negative = BCE)
This path is both the node’s primary key and its API address.

​
SNAG (Social Network Augmented Generation)

SNAG synthesizes and maintains structured social graphs to ground LLM generation in complex group dynamics. Where RAG answers questions from what was written down, SNAG reasons about what people did, felt, and caused. 19 composable mechanisms handle entity states, knowledge provenance, dialog steering, emotional dynamics, relationship tracking, and more. Each mechanism can be enabled/disabled independently.

​
Temporal Modes

Timepoint Pro supports five temporal reasoning modes:
ModeDescriptionUse Case
FORWARDStrict forward causalityStandard timelines, “what happens next”
PORTALBackward from target outcomeGoal decomposition, “how did we get here”
BRANCHINGCounterfactual branches”What if” analysis, alternate histories
CYCLICALFuture constrains pastFeedback loops, self-fulfilling prophecies
DIRECTORIALDramatic tension drives eventsNarrative arcs, screenplay generation

​
Content Layers

The Clockchain stores moments at increasing levels of detail:
LayerContentSource
0URL path + event nameClockchain (auto-generated)
1Metadata: figures, tags, descriptionClockchain expander (LLM)
2Full rendered scene with dialog, characters, imageFlash renderer

​
Edge Types

Moments are connected by typed causal edges:
TypeMeaningAuto-linked?
causesDirect causal relationshipNo — expander or manual
contemporaneousSame year (+/- 1)Yes
same_locationMatching geographyYes
thematicOverlapping tagsYes
Each edge tightens the Bayesian prior — fewer plausible things could have happened in the gaps.

​
TDF (Timepoint Data Format)

JSON-LD interchange format connecting all services. Every TDF record includes:
  • id — canonical URL or service UUID
  • source — which service produced it (flash, clockchain, pro, proteus, snag-bench)
  • provenance — generator, run ID, confidence score
  • payload — source-specific content
  • tdf_hash — SHA-256 of canonicalized payload for content addressing

​
The Flywheel

The system forms a self-reinforcing loop:
  1. Flash renders historical moments into grounded scenes
  2. Clockchain stores them as graph nodes with causal edges
  3. Expander (LLM) discovers related moments and grows the graph
  4. Pro simulates futures from any graph state
  5. SNAG-Bench scores quality across all outputs
  6. More data → stronger Bayesian prior → better renderings → more data