Read the equation
The tuple separates four components of a model instance at time t: learned parameters, persistent memory, runtime state or context, and observation records. This is a bookkeeping convention that makes it possible to specify which component changed. It does not imply that every component is directly observed in the available experiment.
Terms & definitions
| Term | Meaning in this source |
|---|---|
| S_t | Complete bookkeeping state |
| theta_t | Trainable parameters |
| m_t | Persistent memory |
| c_t | Runtime state and context |
| o_t | Observation records |
How it works
Read the definition from its right-hand expression to the quantity on the left. Its surrounding source records the intended input, state, or parameter context. Where the source leaves an operation unspecified, this page preserves that gap.
Assumptions & limits
Source recovery establishes that the expression appears in this record. Its mathematical validity, implementation behavior, and interpretation must be assessed separately. See the linked source and research notes for the checks available for this version.
Original context
Read the surrounding source passage
I use x to identify a particular system, not a universal number shared by all machines. Two instances can begin with the same architecture and parameters while acquiring different runtime histories. Two training runs can also begin at the same checkpoint and later acquire different parameters. A new conversation is not automatically a newly trained model. For bookkeeping, I separate trainable parameters, persistent memory, runtime state and context, and observations: St=(θt,mt,ct,ot). (2.1) Here θt denotes parameters, mt persistent memory, ct runtime state and context, and ot observations. The tuple specifies what a prospective study must distinguish; it does not claim that the present dataset contains every component. During inference with frozen parameters, θt remains fixed while context and activity can change. During training, an optimizer can change trainable parameters. Resetting context, deleting external memory, and restoring a checkpoint therefore intervene on different objects. [Context excerpt; full source linked.]
Exact original notation
{S}_{t}=({\theta }_{t},{m}_{t},{c}_{t},{o}_{t}).Related builds
Sources & provenance
{S}_{t}=({\theta }_{t},{m}_{t},{c}_{t},{o}_{t}).
{S}_{t}=({\theta }_{t},{m}_{t},{c}_{t},{o}_{t}).
{S}_{t}=({\theta }_{t},{m}_{t},{c}_{t},{o}_{t}).
{S}_{t}=({\theta }_{t},{m}_{t},{c}_{t},{o}_{t}).