Gate A: Novelty
Is this line's combination of aims new, or is its difference from the closest published work written down and defensible?
If missed
Reposition the contribution and record the decision privately before work continues.
Start here
Explore the timeline
These are the phases and gates of Psyche's current research line, stage 2: spiking cognitive maps. Every date here is read from one file, the research plan, at build time. A moved date keeps its original alongside it and gets a change-log entry. The text version is in Roadmap.
Now: P0 Novelty review and setup, 23 October 2026 to 15 November 2026
Next gate: Gate A Novelty, 15 November 2026
Timeline
Phases
P0: Novelty review and setup
Active23 October 2026 to 15 November 2026
Outputs
- novelty decision recorded
- development environment
Ends at Gate A (Novelty), on 15 November 2026: Is this line's combination of aims new, or is its difference from the closest published work written down and defensible?
P0 Novelty review and setup
23 October 2026 to 15 November 2026 Active
Gate A (Novelty): 15 November 2026
P1 Environments, battery and baselines
16 November 2026 to 31 December 2026 Planned
Gate B (Comparisons): 31 December 2026
P2 Spiking model
1 January 2027 to 28 February 2027 Planned
Gate C (Spiking model): 28 February 2027
P3 Scaling, ablations and the energy estimate
1 March 2027 to 15 April 2027 Planned
P4 Paper
15 April 2027 to the submission deadline (not yet announced) Planned
Gate D (Paper): one week before the submission deadline
P5 Public release
Starts after submission; end set by the disclosure policy Planned
Gates
Decision gates
Each gate is decided against criteria written before the work it judges. Once a gate is decided, the public record states only the date it was decided and the next step: the line continues to the next phase, extends, or stops. The rest of a decision stays private and moves here only under the disclosure policy. Details in Decision gates.
Gate B: Comparisons
Do the environments, the battery and the baseline agents run, and do the baselines reproduce the behaviour their papers report?
If missed
Extend briefly, then narrow the baseline set to the strongest published reference.
Gate C: Spiking model
Does the spiking model meet its pre-registered behavioural criteria on the battery?
If missed
Shift the submission target; the work proceeds on the safe base and the failure analysis.
Gate D: Paper
Are all figures, the multi-seed results and the ablations in, and have external readers' comments been worked in?
If missed
A workshop paper and a preprint; a later main-track venue.