evidence.md rows 17, 18, 19 on the measured class v3: the chip model, the latency bound, the soundness and bit-exactness

docs/evidence.md

@@ -41,9 +41,9 @@ Versions in the table: `igneum-pow` is the Rust crate at `igneum-pow/Cargo.toml`
 | 14 | Ethereum bytecode runs unchanged, with the documented differences of spec 7.1 | Homepage Build card; litepaper Building | tested by the team | as row 13; fixes `F-exec-A`, `F-exec-B` (spec 7.5) | `tools/evm-smoke/smoke.mjs`: deploy via viem, `increment`, `hashLoop`, `eth_estimateGas`, `eth_getLogs`; `tools/exec-attacks` scenarios 1 and 3; bench-log "execution layer attack fixes" | Deployment, calls, reverts, logs and gas estimates behave as viem expects; chain id 4463; the prototype pgas table gives 0.0095 to 0.028 pgas per gas, below the design's band before calibration, 3 October 2026. 4 October 2026: a transaction that would cross the block's proving budget is refused by the mempool and, if forced in, aborted and charged with its nonce advanced (25 of 25 checks; 30 of 30 malformed cases). Apple M5 Max. The `Prover` precompile, proof records and the shard planner are not in the node | none yet |
 | 15 | Every block is proven, with the proof landing within about a minute at launch | Homepage stats ("~60 s to a proof"); litepaper Proving; roadmap phase 3 gate | implemented | repo `d7e1f89` (GPU proof), `e01a3cc`, `292e800`, `eedd136` (`proving/igneum-prove`: shard cutter, MPT witnesses, shard and aggregator guests); SP1 6.8.1; spec 7.2, 7.6 | `proving/windows-wsl2` (SETUP-PROVER, PROVE-BLOCK) on the RTX 5090; `igneum-prove-host --mode block` on `proving/fixtures/`; bench-log "proving v0 on the RTX 5090" and "proving: devnet v4 shards" | First GPU proof of an Igneum block, 4 October 2026, RTX 5090 (WSL2, SP1 cuda, mining paused): fixture `block-78-increment` (2 transactions), core proof 1.4 s (7.3 MB, verify 0.221 s), compressed proof 2.7 s (1.27 MB, verify 0.038 s), post-state and receipts roots identical to the node's; 15.7x and 20.6x faster than a loaded M5 Max CPU. The same day on that CPU (load 38 to 47): a three-shard block proved shard by shard and aggregated by recursion, 19 min (1,139 s) end to end, 245 to 337 s per compressed shard proof, every proof verified. What is not there: no proof is produced, carried or checked on the chain (the devnet prover is a stub that signs claims), the proving pool pays nobody (row 21), the block proven is far below one shard, and the 60-second figure remains a design target; the pass mark is the standard in `docs/benchmarks/proving-e2e.md`. Second RTX 5090 run, 4 October 2026 evening (job run-20261004-173115): a full shard at the provisional S_p (6.75 M pgas, 60.8 M cycles) executed in 1.63 s, core proof 8.3 s (18.1 MB), compressed proof 10.9 s (1.27 MB, verify 0.040 s); a two-shard block (13.5 M pgas) proved shard by shard (11.7 s and 10.0 s) and aggregated in 2.2 s, 24 s of GPU stages end to end, every proof verified, six tampered witnesses rejected. The two host defects (an abort after the upload, an idle wait that turned out to be an unbuffered 18 MB proof save through the WSL2 file bridge, 24 minutes) are fixed (ledger P20) 5 October 2026, live devnet with real transactions (bench-log "real transactions, the first non-empty shard proven and paid"): block 72704 shard 0, 29 transfers, 5,800 pgas, proven on PC 2 in 34 s, verified on the Mac in 0.297 s and paid 1.7623 IGN, 53 s after the chain block executed; of about 1,400 blocks in the 20-minute window 36 were proven (the one prover takes the newest shard assigned to it), so "every block" is not yet true; a second content shard (72803, all copies skipped) failed the native-execution veto on the exporter's block structure, fixed with fixtures the same day, the node side pending the 0.3.9 rollout | none yet |
 | 16 | A 12 GB card proves one shard in about 20 s | Litepaper Proving ("The proving budget"); roadmap gate 2 | designed | spec 5.1 (Target), 7.6 (`S_p` provisional, 7,500,000 pgas = `B_p` / 4) | `PROVE-SHARD.bat` on the RTX 5090 (pending); the end-to-end standard in `docs/benchmarks/proving-e2e.md`; bench-log "proving: devnet v4 shards" | Measured on a 32 GB card, not yet on a 12 GB card. A shard at the provisional `S_p` is 60.8 M SP1 cycles on the prototype pgas table (9 cycles per pgas, 44 per EVM gas; the modexp entry about 100x its SP1 cost); on an RTX 5090 (4 October 2026 evening, job run-20261004-173115) it executed in 1.63 s and its compressed proof took 10.9 s, verified in 0.040 s, so the 32 GB card is inside the 20 s target with margin. Whether a 12 GB card proves it at all, and in what time, is the next measurement (an RTX 3060 and an RTX 5060 Ti 16 GB are on order). A per-shard time can be met by shrinking the shard, so the project does not use it as a pass mark | none yet |
-| 17 | The chip resistance target: a chip gains under 2x over a GPU | Litepaper Mining, "What Igneum does not claim"; homepage "no chip can be built for it" | designed | spec 0.2 (Target); O-1.17 | Public benchmark with a leaderboard by card model and a standing bounty, January 2027 (O-1.17); the on-die-SRAM test on the RTX 5090 (R3.5) | A target, not a measurement. Review round 3 priced a recompute chip with the 256 MiB cache on die at about 2.4x, approximate, before the usual chip-versus-GPU integer gain; the design answer (cache larger than any die) is open (spec 1.16) | none yet |
-| 18 | The chip resistance measurements: the program is random-access bound, not bandwidth bound, and sits beyond a card's on-chip cache | Litepaper Mining ("bound by memory bandwidth", to be corrected), vs RandomX "Measured so far" | tested by the team | repo `aba248d`, `f2a1a64`, `4b95c5e` | RTX 5090 dataset sweep 4 MiB to 1 GiB with `proto-cuda/host.cu`; bench-log "RTX 5090 first run" and "dataset sweep" | At 1 GiB: 228.1 Mhash/s, 23.7 G random loads/s, 94.9 GB/s useful against a 1,638 GB/s dataset fill; inside the 96 MiB L2 (4 and 64 MiB) 1,340 to 1,353 Mhash/s, about 5.8x faster; 104 against 128 loads per hash gives 228 against 185 Mhash/s, proportional. 3 October 2026, RTX 5090, Windows, CUDA 12.8, version 1 programs. Prototype dataset 1 GiB against 2 GB at genesis; a pure random-read microbenchmark (R3 chip designer, attack 2) has not run; the sweep has not been repeated on version 2 | none yet |
-| 19 | The lottery hash is sound as a hash: uniform output, deterministic, no out-of-bounds read, fuzzed | Litepaper vs RandomX ("Every number above is measured and logged") | tested by the team | repo `c52307e`, `58a5a63`, `b27da39`; `proto-metal/TESTS.md` | `proto-metal/igneum-bench --fuzz --edge --stats --determinism --memcheck`; `--fuzz 2000` on the version 2 generator; `igneum-census`; bench-log "hardening tests", the re-run on the memory-hard dataset, "generator version 2 adopted" | Version 1: 10,200 random programs, 1,305,600 hashes, 0 mismatches; 14 of 14 edge cases; bit frequency within 2.90 sigma, avalanche mean 31.99 to 32.04 of 32; deterministic fingerprint across 5 runs; every dataset read masked, 3 October 2026. Version 2, 4 October 2026: 2,000 random programs through the Metal cross-check, 8,000 warps, 0 mismatches, 128 loads per hash on every program; 20,000-program census, 5.2% rejected (4.1% static, 1.1% dynamic). Apple M5 Max. Statistics are not a security proof; the edge, stats and memcheck sections were not re-run on version 2 (they do not depend on the generator); the seed derivation review (O-1.4) is open; the fuzz set has run on Metal and the CPU only | none yet |
+| 17 | The chip resistance target: a chip gains under 2x over a GPU | Homepage hero and litepaper abstract ("a custom chip gains under 2x, and the model and the bounty are public"), litepaper "What Igneum does not claim" | tested by the team (the model), designed (the target) | program class v3 (Counter ASIC 2.0, 5 October 2026): branches ca2-v3 d233fa1 and after, ca2-mixer 1ab8b21, ca2-era 78c0ee4; `docs/analysis/chip-model-v3.md`, `docs/analysis/sram-mirror.md`, `docs/analysis/scratch-soundness.md` | The m16 recompute model re-run on the measured v3 rates and verifier times; the on-die-cache chip row | The on-die-cache recompute chip against the RTX 5090's measured 136.1 MH/s: class v2 2.4x; class v3 (mixer x8) 0.31x bare, 0.92x with a 3x fixed-function allowance (approximate), 0.76x at equal silicon; margin 8% on the allowance, 9% on the budget. 5 October 2026, M5 Max, RTX 5090, RX 9070 XT. The 2x target is a target: no chip has been built; the bounty stands (O-1.17) | none yet |
+| 18 | The chip resistance measurements: the program is latency-bound (random reads), not bandwidth-bound, on every card we own, and sits beyond a card's on-chip cache | Litepaper Mining ("waits on memory latency, not on maths or bandwidth"), vs RandomX; the numbers page | tested by the team | readwidth e752fc7 (`docs/plans/read-width.md`), ca2-era 78c0ee4, ca2-cache 2de19e5 (`docs/plans/hot-table.md`) | The dependent-read probes at 32 to 1,024 MiB and the hash rate per class on the three cards; the latency-bound share = rate over the probe ceiling per load | Latency-bound share at the 1 GiB dataset: RTX 5090 0.96 (v2) and 1.01 (v3), RX 9070 XT 0.87 and 0.95, M5 Max 1.01 and 1.06; wider reads do not close the AMD gap (the 9070 XT does 2.4 G dependent reads per second at every width; the 5090 goes bandwidth-bound at 64 B, share 0.58); a 32 to 96 MiB hot table is not kept resident by any card while the dataset streams (g 0.80 to 0.87 in the added form). 5 October 2026 | none yet |
+| 19 | The lottery hash is sound as a hash: uniform output, deterministic, no out-of-bounds read, fuzzed; class v3 bit-exact on the three vendors | Litepaper vs RandomX ("Every number above is measured and logged"), the numbers page | tested by the team | ca2-mixer 1ab8b21 (`tests/mixer.rs`, `tests/scratch.rs`), ca2-era 78c0ee4, ca2-soundness a465881 (`docs/analysis/scratch-soundness.md`), `igneum-pow/tests/packs.rs` | The crate suite (53 + 4 + 19 + 7), the Metal fuzz, edge, stats and determinism runs on the v3 construction, the pack vectors and 2^24 fingerprints on Metal, Apple OpenCL, the RTX 5090 and the RX 9070 XT, the 1,024-hash CPU re-check per card | Class v3 (mixer x8 + era): 200-program fuzz 200 of 200 on Metal, every tenth on Apple OpenCL; the pinned v3 packs 3/3 + 3/3 and 96 of 96 lanes on Metal and Apple OpenCL; the six era packs' fingerprints equal on the three vendors (PC 1 job run-ca2-era-pc1-20261005, 5 October 2026); the v2 exports byte-identical on the v3 crate; the final-class PC rows and the G2 re-check: job run-ca2-era-pc1b-20261005 (pending at the time of writing) | none yet |
 | 20 | No premine, no pre-sale, no allocation: every coin is minted by the schedule and every coin goes to the block producer (80%) and the proving pool (20%) | Homepage stats and Economics tiles; litepaper Supply, Economics | implemented | repo `6ac80a3`; fork "igneum-node devnet v0"; `consensus/core/src/igneum.rs`, `coinbase.rs` | `cargo test -p kaspa-consensus-core igneum` (8 pass: subsidy table, ramp, split, cap) and `cargo test -p kaspa-consensus coinbase` (8 pass); `igneum-miner inspect 40`; bench-log "igneum-node devnet v0" | Coinbases on the devnet: 80/20 exact on 39 of 39 single-payee blocks, the 20% to the `igneum-proving-pool-v0` output; the per-second schedule sums to under the 4,000,000,000 cap by less than 100 coins; 3,168,808,781 units per DAA second in years 0 to 2, halving at 63,115,200 DAA s. 3 October 2026, Apple M5 Max. The devnet genesis carries no allocation; the mainnet genesis does not exist yet, so the claim is about the code and the stated rule, not a launch that has happened | none yet |
 | 21 | The proving pool's 20% reaches shard provers and aggregators | Litepaper Economics; homepage "20% provers" | tested by the team | spec 5.3; `proving/igneum-prove` carries the prover's payout address in every shard proof (ledger P12) | None. The pool output exists (row 20); the payout from it against proof records is unwritten. Since 5 October 2026: the payout rule is live on the devnet (`proving.rs shard_payouts`, the carrying segment pays the first valid record per shard its part of the segment's pool credit) | The escrow accumulated on the simnet (92.55 IGN at the end of the v3 run) and nothing can draw it. Rule decided: per block, divided among shards by consensus proving cost, sortition to 8 provers for 10 s then open (spec 7.2). The economy model of 4 October 2026 (`sim/economy`, 1,000 operators, 30 days) kept every block proven within 60 s under six stress scenarios; a model, not hardware Live devnet, 5 October 2026: 388 shards paid by 16:02 UTC, 446.13 IGN from the pool to PC 2's payout address, 0.8813 IGN per mergeset block of the proven segment (bench-log entries of 5 October: "the first shards proven, verified and paid" and "real transactions, the first non-empty shard proven and paid") | none yet |
 | 22 | The base fee is burned in full and the priority fee splits 80% to the miner and provers, 20% to the apps whose code ran | Homepage Economics caption and Build card; litepaper "Where fees go" | tested by the team | repo `f5f8c80`; fork worktree `vendor/igneum-node-exec` | `tools/evm-smoke/smoke.mjs` receipt checks; bench-log "execution layer devnet v3" | Transfer receipt: `burnedProvingFee` 200 gwei, `minerTip` 16,800 gwei (80%), unregistered developer share 4,200 gwei burned; contract call: 80% to the miner, 20% credited to the payee the constructor registered, balance delta equal. 3 October 2026, Apple M5 Max simnet. The provers' part of the 80% is not split out (no provers exist); the base fee stayed at the 1 gwei floor throughout | none yet |