* feat(timesfm): TimesFM 1.0 200M decoder-only inference port to candle
Native Rust/candle port of google-research/timesfm (pytorch_patched_decoder.py)
for temporal embeddings + zero-shot forecasting inside RuVector. Behind an opt-in
`candle` feature (default = [], cpu-fallback pattern like ruvector-hailo); no
lockfile churn (candle 0.9.2 already pinned by ruvllm).
- config.rs: TimesfmConfig (1280 dim, 20 layers, 16 heads, 80 head_dim, patch 32/128)
- model.rs: ResidualBlock patch embedding, sinusoidal pos-emb (no RoPE), 20x decoder
(fused qkv, learnable per-head-dim softplus scaling, causal+padding mask), RevIN
instance norm, forward [B,N,128,10] + autoregressive decode to arbitrary horizon
- scripts/convert_weights.py: HF safetensors → VarBuilder key remap (--dry-run)
- 12 tests (shape + RevIN numerical regression); clippy -D warnings clean
Adversarial review caught + fixed a real RevIN bug (masked_mean_std did a global
mean/std instead of the reference's first-qualifying-patch selection) + added
regression tests. Honest scope: dimensionally + structurally faithful, but real
numerical weight-parity vs the published safetensors is NOT yet verified (tests
run on dummy weights). Open low-impact faithfulness deviations documented in code.
Co-Authored-By: claude-flow <ruv@ruv.net>
* style(timesfm): rustfmt the crate (format the RevIN-fix edits) — green the Rustfmt gate for this crate
Our crate is now fmt-clean + clippy-clean; the remaining workspace-wide fmt
diffs are pre-existing in other crates, out of scope for this PR.
Co-Authored-By: claude-flow <ruv@ruv.net>
* feat(timesfm): weight-parity validated against official PyTorch reference
Drives the candle TimesFM 1.0 200M port from "compiles on dummy weights" to
a real numerical PASS against google/timesfm-1.0-200m.
Measured (f32 CPU, deterministic 512-pt series, horizon 128):
max-abs-diff = 8.58e-6 MAE = 3.25e-6 rel-error = 5.83e-7
(target was <1e-2; we hit the f32 accumulation floor ~1e-5.)
Bridge: the real torch_model.ckpt state_dict (253 keys) maps 1:1 through
scripts/convert_weights.py with zero unmapped/missing keys.
Bug found + fixed (src/model.rs build_mask): the attention mask used
f32::NEG_INFINITY for masked positions. With real 0/1 paddings the padding
term `padding * -inf` computes `0 * -inf = NaN`, poisoning the whole mask
so softmax emitted NaN for every row (every forecast value was NaN). The
old `nan_to_zero` guard silently failed (where_cond dtype mismatch -> fallback
`NaN * 1 = NaN`). Replaced with the reference's large *finite* negative
(-0.7 * f32::MAX) and element-wise `minimum` merge, exactly matching
convert_paddings_to_mask + causal_mask + merge_masks. No NaN, exact parity.
Added:
- examples/parity.rs end-to-end parity runner with metrics + verdict
- tests/parity.rs gated integration test (skips cleanly w/o the
814MB artifacts; never fabricates a pass)
- scripts/gen_reference.py reference forecast generator (official decoder)
Co-Authored-By: claude-flow <ruv@ruv.net>
* bench(timesfm): forward-only latency bench — 45ms/forecast (200M, ctx512/h128, warm CPU); parity validated 8.58e-6
* feat(timesfm): predictive-pruning module for Darwin (ADR-191 §2)
Add crates/timesfm/src/prune.rs: forecast an optimization curve's plateau
from its first K points with TimesFM and decide PRUNE vs CONTINUE against a
viability threshold (lower=better, like exploitability). Decoupled — operates
on a generic Vec<f32>, no cross-repo poker-darwin dep.
- decide_prune(): forecast tail to target horizon, plateau = mean of last
horizon/4 steps; PRUNE iff plateau > threshold. Guards: non-finite forecast
=> CONTINUE conf 0 (never kill on a broken forecast); already-viable
(best_so_far <= threshold) => CONTINUE. Scale-invariant confidence.
- examples/predictive_prune.rs + tests/prune.rs: two synthetic curves with
REAL weights — doomed (floor 0.20) => PRUNE (forecast plateau 1.98, conf
0.72); healthy (already below 0.05) => CONTINUE. Both decisions correct.
Skips cleanly when weights absent (no fabricated pass).
- Honest calibration note: TimesFM mean-reverts upward on short synthetic
decays so absolute plateau is biased high; decision rides the robust
relative-ordering + already-viable signals, not absolute calibration.
- Doc-comment shows how poker-darwin calls this on its champion curve.
Tests: 12 shape + parity + prune = 14/14 green (candle); light build green.
Co-Authored-By: claude-flow <ruv@ruv.net>
* test(timesfm): bench24 harness for GCP 24-case deployment test (ADR-191 Phase B)
24 distinct forecast cases (varied period/trend/amp/noise/freq_id; ctx=512,
horizon=128) on real weights. Per-case latency + finiteness assert, aggregate
mean/p50/p95/p99, throughput, peak RSS, machine-readable JSON line. Non-finite
output is a hard FAIL (exit 1), never a silent pass.
Local baseline (ruvultra, 32-thread CPU): 24/24 finite, mean 42.5ms p95 44.2ms,
throughput 23.5 fps, peak RSS 1.55GB.
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(ci) + feat(timesfm): README, publish=true, research-nightly shard, rustfmt
CI fixes:
- timesfm added to research-nightly shard (-p timesfm)
- timesfm excluded from core-and-rest shard (--exclude timesfm)
- cargo fmt -p timesfm: model.rs + 4 example files formatted
- cargo fmt -p ruvector-graph: typed_graph_bench.rs + 4 src files
(pre-existing rustfmt failure blocking the PR)
crates/timesfm/README.md (new):
- Architecture diagram (ResidualBlock → 20× decoder → RevIN → output)
- Feature flags table (candle/cuda/metal/hub)
- Quick-start: inference + weight loading workflow
- Known limitations section (weight parity, MLP mask, pos-emb shift)
- References (ICML 2024 paper, HuggingFace model card)
crates/timesfm/Cargo.toml:
- publish = true (was false)
- readme = "README.md"
Co-Authored-By: claude-flow <ruv@ruv.net>
* chore: cargo fmt ruvector-proof-gate (pre-existing rustfmt CI blocker)
Co-Authored-By: claude-flow <ruv@ruv.net>
* chore: cargo fmt temporal-coherence + tiny-dancer-core (pre-existing)
Co-Authored-By: claude-flow <ruv@ruv.net>
* chore: cargo fmt tiny-dancer-node + ruvllm openmythos (pre-existing)
Co-Authored-By: claude-flow <ruv@ruv.net>
* chore: cargo fmt rvf-runtime/store.rs (pre-existing)
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(ci): timesfm tests run with --features candle in research-nightly
The research-nightly shard was running timesfm without --features candle,
causing a compile error (all model code is behind the feature gate).
Fix: remove timesfm from the shared nextest run; add a dedicated step
that runs only timesfm tests with --features candle.
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(ruvllm): remove broken private-item doc link (DepthLora)
Code Quality CI was failing: public doc in mod.rs linked to private
recurrent::DepthLora. Replace with plain backtick name.
Pre-existing issue surfaced by rustfmt touching the file.
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(ruvllm): fix all private-item rustdoc links in openmythos/mod.rs
Three doc comments linked to private items (LtiInjection, RecurrentBlock,
DepthLora) in the recurrent module. rustdoc's -D warnings caught them.
Replaced with plain-text names. Pre-existing, surfaced by rustfmt touching
the file.
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(ruvllm): fix private attention module doc link
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(timesfm): gate bench/bench24 examples behind candle feature
The bench and bench24 examples import candle_core/candle_nn/timesfm::model
unconditionally, breaking Clippy and stock workspace builds that run without
--features candle. Add [[example]] required-features = ["candle"] so they are
skipped when the feature is off, matching parity/predictive_prune which already
self-gate via #[cfg(feature = "candle")].
Co-Authored-By: claude-flow <ruv@ruv.net>
* fix(maxsim): add ruvector-maxsim to workspace + make clippy-clean
The research-nightly CI shard referenced -p ruvector-maxsim (added
|
||
|---|---|---|
| .. | ||
| examples | ||
| src | ||
| tests | ||
| Cargo.toml | ||
| README.md | ||
ruvector-proof-gate
Tamper-evident vector writes — a Merkle / hash-chain write-ahead log that gives every write to a vector store cryptographic evidence of what was stored, when, and by whom. Part of the ruvector ecosystem.
Every major vector DB (Qdrant, Milvus, Weaviate, LanceDB, FAISS) accepts writes with zero integrity evidence. This crate closes that gap — the defense against silent memory poisoning (the MemoryGraft attack, arxiv 2512.16962).
What it gives you
Admit a WritePayload, get a WriteReceipt you can store alongside the index entry and verify
offline. The gate's chain root is a cryptographic commitment to the entire ordered write log: any
mutation, insertion, deletion, or reorder of writes produces a different root.
Gates
| gate | per-write cost | property |
|---|---|---|
NullGate |
~0 | baseline (no integrity) — throughput ceiling |
HashChainGate |
O(1), ~700 ns | sequential SHA-256 chain; full re-derivation via verify_integrity() |
MerkleGate |
O(log n) | Merkle Mountain Range; supports inclusion proofs |
Usage
use ruvector_proof_gate::{HashChainGate, WriteGate, WritePayload};
let mut gate = HashChainGate::new();
let receipt = gate.admit(&WritePayload::new(id, vector).with_agent(agent_id))?;
// store `receipt` with the index entry; later:
assert!(gate.verify_receipt(&receipt)); // ~6 ns
assert!(gate.verify_integrity()); // full cryptographic re-derivation of the chain
let root = gate.chain_root(); // publish/anchor this commitment
Performance
Measured (DIM=128): HashChainGate.admit ≈ 700 ns/write (~1.4 M/s), verify_receipt ≈ 6 ns
(157 M/s). The integrity tax is ~675 ns/write — negligible next to the HNSW insertion a real write
already performs.
Guarantees (tested)
- Any mutation / insertion / deletion / reorder changes the root.
- Forged commitments, out-of-range receipts, and foreign-chain receipts are rejected (no panic).
verify_integrity()re-derives every commitment from genesis + stored payload hashes — it catches a tamper that mutates a commitment, a payload hash, the order, or desyncs lengths.
Features
serde— derive serialization for receipts (off by default).
License
MIT OR Apache-2.0 © Ruvector Team. See ADR-194 for design notes.