Skip to content

nn/hslm: add the per-block VSA stream of the trained HSLM #10099

Closed as not planned

Description

@gHashTag

What

After #10062 (PR #10068), the nn/hslm spec has the trained shape of the HSLM that gHashTag/trinity-training trained (src/hslm @3e9648c1), but it still leaves out the per-block VSA stream from trinity_block.zig / model.zig forwardTrain. In that stream each block binds and rotates the trit sequence and gates on max similarity >= PHI_INV. When the gate fires, the block adds 0.1 * project(context) to its output, and the next block takes that output as its input.

The ternary STE update (shadow weights, TWN requantize, the STE backward) is not in this issue's scope. It belongs to the STE lane, #10076.

The conformance file nn_hslm_vectors.json still describes the 6-layer, FF 972, ctx 81 model, and nothing reads it.

Boundary

  • specs/nn/hslm.t27
  • specs/igla/own_model.t27
  • specs/igla/own_model_board.t27
  • conformance/nn_hslm_vectors.json
  • .trinity/seals/HSLM.json
  • .trinity/seals/nn_HSLM.json

User Scenarios

  • Given the spec at position 0, when every block runs, then every gate fires and the VSA stream hands the block input on unchanged.
  • Given the probe token at position 1, when block 0 runs, then its similarity stays under PHI_INV, the gate stays shut, and the output equals the stream-off output.
  • Given the stream on, when the gradient checks run, then every central-difference check still passes, because the stream never reads a float parameter.

Requirements

  • Write .t27 only; no hand-written foreign code.
  • The VSA offset does not depend on the float parameters, so the existing finite-difference gradient checks still hold with the stream on.
  • Add a mutation control: a gate mutant and a gain mutant each fail at least one test.
  • Raise own_model's forward-pass cell and mirror the change in own_model_board; leave the STE cells to spec(own-model): ternary STE, HSLM backward and data/checkpoint layout in t27 (cells 16-18) #10076.
  • Delete the stale conformance file.

Success Criteria

  • t27c test-report specs/nn/hslm.t27 on the Railway lab: 0 FAIL, 0 vacuous.
  • t27c test-report of specs/igla/own_model.t27 and specs/igla/own_model_board.t27: 0 FAIL, 0 vacuous.
  • t27c seal specs/nn/hslm.t27 --save re-saves .trinity/seals/HSLM.json and .trinity/seals/nn_HSLM.json.
  • Each of the 2 mutants fails at least 1 test.

Activity

  1. added a commit that references this issue on Oct 17, 2026
    cc56fcf
  2. changed the title [-]spec(hslm): nn/hslm runs the VSA stream and the trainer's ternary STE step[/-] [+]nn/hslm: add the per-block VSA stream of the trained HSLM[/+] on Oct 17, 2026
  3. added
    shape-refusedClosed by the issue-shape gate (specs/policy/issue_shape.t27); a passing edit reopens it
    on Oct 17, 2026
  4. github-actions commented on Oct 17, 2026

    @github-actions
    Contributor

    Closed by the issue-shape gate (specs/policy/issue_shape.t27, #7498): an issue must have the template's sections. Edit the body; an edit that passes reopens it.

    • missing: ## Requirements -- numbered obligations, FR-001: ... MUST ...
  5. added 2 commits that reference this issue on Oct 17, 2026
    01fc4ce
    cd9018c
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    shape-refusedClosed by the issue-shape gate (specs/policy/issue_shape.t27); a passing edit reopens it

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions