docs: LOOPS_AND_RECURRENCE.md — how LSTM/GRU/Mamba/scan work in nFlow (DAG-based, explicit unrolling + nn.scan pattern)

docs: Session 8 final — compile fixes, architecture diagram, expected test count

docs: Session 8 — custom node creator full system summary

docs: Session 7 handoff — .nfl format, file I/O, File menu, wgpu architecture clarification

docs: Session 6 final — 90/90 exec coverage achieved, 174 tests

docs: Session 6 handoff — 84/90 exec, 11 new kernels, 171 tests

docs: Session 5 handoff summary

docs: OPERATORS.md — Session 5 summary (batched_matmul, groups conv, groupnorm, ~71 ops)

docs: Session 4 handoff — run_forward, exec kernels, coverage audit, RunPanel UI, 150 tests

docs: 3-way simulator/PyTorch/Keras parity verified

docs: verified simulator<->PyTorch export parity

docs: one-click forward pass (run_forward + RunResultView)

docs: exec_coverage Tauri command + api.execCoverage() frontend surface

docs: nn.linear ONNX mapping = Gemm

docs: execution coverage audit API + io node passthrough

docs: embedding/dropout/batchnorm execute (~61 ops)

docs: exact multi-head MHA + reshape-0 lowering + post-lower inference

docs: layernorm/rmsnorm execute numerically (~58 ops)

docs: pooling kernels execute; full CNN forward pass runs in numeric runtime (~56 ops)

docs: nn.conv2d now executes numerically (direct NCHW conv, owned ParamSpec)

docs: nn.linear executes numerically via owned ParamSpec (deterministic seeded materialization)

docs: composite blocks now expose attrs in inspector

docs: exec now ~50 ops (reductions + flatten/squeeze/unsqueeze)

docs: attention 1/sqrt(d_k) scaling now numerically exact

docs: all movement ops now have CPU numeric kernels

docs: movement.transpose/concat/gather/onehot now have CPU numeric kernels

docs(operators): document math.scale

docs: document expanded nflow-exec CPU numeric kernel coverage (~37 ops) + exec step in 'adding an operator'

docs(operators): document movement.onehot

docs(operators): document movement.gather

docs(operators): document movement.slice

docs(operators): document movement.pad / tile / expand

docs: e2e verification + Keras from_logits loss-instance fix

docs: frontend TrainPanel editor

docs: SetTrainConfig intent + editing path

docs: training-config / optimizer codegen (per-backend slot translation)

docs: add Loss operators section + framework-asymmetric loss export (83 prims)

docs: sync catalog (76 prims) with flow.where + math.clip

docs: sync operator catalog (74 prims) + param-ownership note with new ONNX/Keras-parity ops

Add param-ownership + symbolic shape engine architecture; update operator catalog

Update ML Intern artifact metadata

Add param-ownership + symbolic shape engine architecture; update operator catalog

initial commit