knowledge: distinguish Xe-Forge trial origin and timing

docs/reference-matrix.md

@@ -248,6 +248,7 @@ SSD/OS systems columns.
 | JiusiServe/vllm-evolve @ 43cc82c | search | scheduling-algorithm evolution, search policy | `optimization-search-policy`, `dense-performance-evidence`, `inference-benchmark-design` |
 | [OpenBMB/JustGoal repo + paired paper](https://github.com/OpenBMB/JustGoal/tree/f052fc0b28fc7f10b2ef1ae7aa4682aabbbe868d) @ `f052fc0b28fc7f10b2ef1ae7aa4682aabbbe868d` (repository Apache-2.0 default; NOTICE BSD exceptions; paper license UNKNOWN) | evaluation | Bounded direct inspection, 2026-11-02: complete 21-page paper/appendices and selected DSA wrapper/CUDA workspace/stream contracts; [exact readset and exclusions](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-source.json). Source-only methodology; author-reported comparisons, released failures versus repaired timing and official/stricter oracle differences retained | [inference-benchmark-design reference](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/justgoal-evaluation-contracts.md); candidate/not_run, efficacy not_evaluated; no new implementation/backend coverage or full campaign runner |
 | [AutoTuneBench repo + paper v1](https://github.com/li-ch/autotunebench/tree/64cc8d7ca5d0ee40c4e2189b2c2c8dfb1a2a7c2f) @ `64cc8d7ca5d0ee40c4e2189b2c2c8dfb1a2a7c2f`; [arXiv:2609.18123v1](https://arxiv.org/abs/2609.18123v1) (selected repository code/data MIT; paper CC BY 4.0) | evaluation | Bounded source inspection, 2026-11-02: treatment delivery, arm-validity precedence, exported protocol/check/record gaps, weak-denominator and anomaly counterexamples; complete 15-page paper, 6 figures, 7 tables and [exact selected readset/rights](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-source.json) | [inference-benchmark-design reference](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-trial-validity.md); source-derived candidate/not_run, efficacy not_evaluated; invalid-arm/source-median conflicts retained, no new controller or measured implementation coverage |
+| [Xe-Forge repo + paper v1](https://github.com/IntelLabs/Xe-Forge/tree/6cd3ee98dfe32746b345a6abe521fa4cb9bdc187) @ `6cd3ee98dfe32746b345a6abe521fa4cb9bdc187`; [arXiv:2605.26118v1](https://arxiv.org/html/2605.26118v1) (repository Apache-2.0; paper CC BY 4.0) | evaluation | Bounded source inspection, 2026-11-02: 18-file trial identity/origin, external outcome, selection/finalization/reporting and baseline-oracle readset; complete paper HTML/appendix/tables/algorithm/listing/captions, unused graphic values unverified; [exact hashes, rights and exclusions](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-source.json) | [`inference-benchmark-design` reference](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-trial-evidence.md); candidate/not_run, efficacy not_evaluated; two measured meanings, named-verdict update limits and manual versus measured-only defaults retained; no runtime integration or whole-model/backend promotion |
 | Dong1017/OmniRSI @ `codex/skill-eval-bootstrap` (82218b4) | evaluation | skill_distill / skill_eval harness, no_skill/human/distilled contract, Tier A pilot | `npu-skill-factory` (evaluation contract) |
 | InferMatrixLab/InferRSI PR #9 @ 4ad551a9 | reference | `skill_library/` layout + knowledge records | `npu-skill-factory` (bundle layout) |
 | RRSI — arXiv 2609.24972v3 | search; mined via reviewed Pack F | bounded harness proposals; calibrated noise/cost/novelty gates; grouped-ablation limits, replacing the earlier generic constraint summary | `optimization-search-policy`; [exact ledger](../src/inferrsi/data/skill_library/methods/optimization-search-policy/references/papers-20261015/references/source-notes.md#f1--rrsi) |

docs/searchspace-matrix.md

@@ -600,6 +600,12 @@ NOASSERTION and InferRSI's repository license.
 | --- | --- | --- | --- |
 | Accelerator (methodology only) | Verify: trace treatment to the eligible consumer, apply frozen arm validity before interpreting a null, and separate declared protocol, reached checks and persisted gate evidence | [inference-benchmark-design reference](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-trial-validity.md) and [source record](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/autotunebench-source.json); AutoTuneBench repo + paired paper | Source-derived candidate / empirical not_run; paper measurements remain author-reported, efficacy not_evaluated. Contextual source bars are not InferRSI defaults. No new implementation, measured hardware/resource coverage, backend compatibility, or RAM/Storage/Network/OS coverage. |
 
+## Xe-Forge trial-evidence guidance (source-derived)
+
+| Resource | Stage and mechanism | Source and owner | Evidence boundary |
+| --- | --- | --- | --- |
+| Accelerator (methodology only) | Verify: bind saved candidate and comparator identities, distinguish tool origin from resolved performance, inspect host gate/ratio persistence, and follow manual versus measured-only delivery and baseline-oracle boundaries | [inference-benchmark-design reference](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-trial-evidence.md) and [source record](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/references/xeforge-source.json); Xe-Forge repo + paired paper | Source-derived candidate / empirical not_run; paper/README results remain author-reported, efficacy not_evaluated. No new implementation, measured hardware/resource coverage, backend compatibility, whole-model/service promotion or RAM/Storage/Network/OS coverage; draft extensions remain proposals. |
+
 ## TorchNPU framework source procedures
 
 | Resource | Stage / mechanism | Canonical owner | Evidence boundary |

docs/skill-coverage.md

@@ -4,7 +4,7 @@ Generated from the registry, the skill sidecars and the two maintained
 matrices. **Do not edit by hand**; regenerate after any registry, skill,
 matrix or frozen-plan change.
 
-- Input digest: `sha256:7640b171256091efd1514a33d5e434eef3feaed238fc92fe3eeba02fee94e9ff`
+- Input digest: `sha256:0dcdead4b319f996fcf0f1a3125de5f1ae4717ba6c8aa34cb3f1fa6dbf5494f3`
 - Regenerate: `python tools/build_skill_coverage.py`
 - Verify without writing: `python tools/build_skill_coverage.py --check`
 
@@ -131,7 +131,7 @@ optimization is fully covered or that any procedure has measured benefit.
 | [choose-parallel-training-plan](../src/inferrsi/data/skill_library/methods/choose-parallel-training-plan/SKILL.md) | common | Compare stage, device-mesh and operator-sharding candidates for static distributed training while accounting for ... | Comparing stage, device-mesh and operator-sharding candidates for static distributed ... | failure_modes, input_contract, produced_artifact, refusal_point<br>3 advice | 1 Accelerator · Diagnose / Configure / Optimize / Verify<br>4 Network · Diagnose / Configure / Optimize / Verify | 1 · Systems sources (Alpa — [2201.12023v3](https://arxiv.org/abs/2201.12023v3)) | candidate · not_run · 1 readset(s) | no-eval |
 | [dense-performance-evidence](../src/inferrsi/data/skill_library/methods/dense-performance-evidence/SKILL.md) | common | Taxonomy of performance evidence an optimization agent needs, ordered by collection cost and diagnostic power. Maps ... | Deciding which performance evidence to collect next and which claim each evidence level ... | failure_modes, input_contract, produced_artifact, refusal_point<br>4 advice | 1 Accelerator · Observe / Profile / Verify<br>2 RAM/Host · Verify<br>4 Network · Verify | 1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd)<br>2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)<br>2 · Methodology and corpus references (microsoft/SkillOpt @ 343db22) | candidate · not_run · 0 readset(s) | — |
 | [evaluate-elastic-serving-placement](../src/inferrsi/data/skill_library/methods/evaluate-elastic-serving-placement/SKILL.md) | common | Compare migrating an LLM request between model replicas with changing its sequence-parallel execution group, including ... | Comparing migration of a running LLM request between compatible model replicas with ... | failure_modes, input_contract, produced_artifact, refusal_point<br>3 advice | 1 Accelerator · Diagnose / Configure / Optimize / Verify<br>2 RAM/Host · Diagnose / Configure / Optimize / Verify<br>4 Network · Diagnose / Configure / Optimize / Verify | 1 · Systems sources (Llumnix — [2406.03243v1](https://arxiv.org/abs/2406.03243v1)) | candidate · not_run · 1 readset(s) | no-eval |
-| [inference-benchmark-design](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md) | common | Select task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents ... | Selecting task quality gates, reference parity checks and performance workloads for text ... | failure_modes, input_contract, produced_artifact, refusal_point<br>5 advice | N/A: SKILL.md §§ Select the task and its evaluation contract, Statistical requirements, Shared-machine measurement discipline, and Search integrity and final-state verification design comparable evaluation; hardware identity and allocation isolation are comparison controls, not a hardware-resource mechanism. | 2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)<br>Task-specific benchmark selection (issue #60) ([Issue #60 report](https://github.com/InferMatrixLab/InferRSI/issues/6 ...)<br>Task-specific benchmark selection (issue #60) ([NVIDIA/NeMo-Speech.cpp @ 20999cc9](https://github.com/NVIDIA/NeMo-Spe ...) | candidate · not_run · 7 readset(s) | — |
+| [inference-benchmark-design](../src/inferrsi/data/skill_library/methods/inference-benchmark-design/SKILL.md) | common | Select task quality gates, reference parity checks and performance workloads for text, agentic coding, work agents ... | Selecting task quality gates, reference parity checks and performance workloads for text ... | failure_modes, input_contract, produced_artifact, refusal_point<br>6 advice | N/A: SKILL.md §§ Select the task and its evaluation contract, Statistical requirements, Shared-machine measurement discipline, and Search integrity and final-state verification design comparable evaluation; hardware identity and allocation isolation are comparison controls, not a hardware-resource mechanism. | 2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)<br>2 · Methodology and corpus references ([Xe-Forge repo + paper v1](https://github.com/IntelLabs/Xe-Forge/tree/ ...)<br>Task-specific benchmark selection (issue #60) ([Issue #60 report](https://github.com/InferMatrixLab/InferRSI/issues/6 ...)<br>Task-specific benchmark selection (issue #60) ([NVIDIA/NeMo-Speech.cpp @ 20999cc9](https://github.com/NVIDIA/NeMo-Spe ...) | candidate · not_run · 9 readset(s) | — |
 | [inference-optimization-casebook](../src/inferrsi/data/skill_library/methods/inference-optimization-casebook/SKILL.md) | common | How to structure and use a casebook of past optimization decisions as a decision-support tool. Extracts the casebook ... | Structuring and querying a casebook of past optimization decisions as decision support ... | failure_modes, input_contract, produced_artifact, refusal_point<br>4 advice | 1 Accelerator · Optimize | 1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd) | candidate · not_run · 0 readset(s) | no-eval |
 | [kernel-writing-guide](../src/inferrsi/data/skill_library/methods/kernel-writing-guide/SKILL.md) | common | Decision guide for writing custom inference kernels: when to write one, which framework to choose (Triton, CuTe DSL ... | Deciding whether to write a custom inference kernel, routing a kernel pattern to Triton ... | failure_modes, input_contract, produced_artifact, refusal_point<br>6 advice | 1 Accelerator · Optimize / Diagnose / Configure / Verify | 1 · Systems sources (Dao-AILab/causal-conv1d @ `cd81f0413cad2fc1e6f17e785ac39f59aae690cd` ...)<br>1 · Systems sources (NVIDIA/TensorRT-LLM @ f33e0e5fd)<br>1 · Systems sources (huggingface/transformers @ `0dad7b822255a0ae261ec45ae937371e859ffd1a` ...)<br>1 · Systems sources (mindspore-ai/akg @ `5aa15f3fe4d856eb60cd3b27447e04f5f1fb4dff` ...)<br>1 · Systems sources (sgl-project/sglang @ `16176278d0180f1a1a578e53e6eef432577876c2` ...)<br>1 · Systems sources (vllm-project/vllm @ `537a79f0fc5ba564d2bef43d54915b2f80f9f77d` (root ...) | candidate · not_run · 7 readset(s) | no-eval |
 | [optimization-search-policy](../src/inferrsi/data/skill_library/methods/optimization-search-policy/SKILL.md) | common | Policy for how an optimization agent should select, order, and stop optimization experiments. Covers candidate ... | Selecting, ordering and stopping optimization experiments: candidate generation ... | failure_modes, input_contract, produced_artifact, refusal_point<br>4 advice | 1 Accelerator · Optimize | 2 · Methodology and corpus references (JiusiServe/vllm-evolve @ 43cc82c)<br>2 · Methodology and corpus references (RRSI — arXiv 2609.24972v3)<br>2 · Methodology and corpus references (arXiv 2608.01867 (CRISP))<br>2 · Methodology and corpus references (microsoft/SkillOpt @ 343db22) | candidate · not_run · 9 readset(s) | no-eval |

src/inferrsi/data/repo_packs/inferrsi/knowledge/README.md

@@ -15,7 +15,7 @@ These are knowledge abstracts (`--kind knowledge`), with namespaced package
 IDs distinct from explicitly selected `checkout_ref` skills. Ascend/CUDA
 procedures use their corresponding backend; shared methods use `common`.
 
-Source snapshot: [7aa3344bf84c42467f43b3a927e1c7d13642bd55](https://github.com/InferMatrixLab/InferRSI/tree/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library).
+Source snapshot: [bb4720992ac2a515adc09b645e1e3cfda47e9d69](https://github.com/InferMatrixLab/InferRSI/tree/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library).
 
 ```bash
 inferrsi knowledge search 'profiling' --repo-type inferrsi --limit 50
@@ -29,7 +29,7 @@ contain the current input paths and bytes (Git checkout filters are respected).
 
 ```bash
 python tools/build_skill_index.py --source-revision <committed-source-revision>
-python tools/build_skill_index.py --source-revision 7aa3344bf84c42467f43b3a927e1c7d13642bd55 --check
+python tools/build_skill_index.py --source-revision bb4720992ac2a515adc09b645e1e3cfda47e9d69 --check
 ```
 
 `--check` detects missing, stale and unexpected generated records without writing.

src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-aclgraph-capture-replay.json

@@ -21,8 +21,8 @@
   "sources": [
     {
       "type": "git",
-      "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md",
-      "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+      "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md",
+      "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
       "paths": [
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/SKILL.md",
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-aclgraph-capture-replay/metadata.json",

src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-device-health.json

@@ -23,8 +23,8 @@
   "sources": [
     {
       "type": "git",
-      "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md",
-      "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+      "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md",
+      "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
       "paths": [
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/SKILL.md",
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-device-health/metadata.json",

src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-distributed-parallel.json

@@ -27,8 +27,8 @@
   "sources": [
     {
       "type": "git",
-      "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md",
-      "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+      "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md",
+      "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
       "paths": [
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/SKILL.md",
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-distributed-parallel/metadata.json",

src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-graph-mode.json

@@ -26,8 +26,8 @@
   "sources": [
     {
       "type": "git",
-      "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md",
-      "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+      "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md",
+      "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
       "paths": [
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/SKILL.md",
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-graph-mode/metadata.json",

src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-model-adaptation.json

@@ -22,8 +22,8 @@
   "sources": [
     {
       "type": "git",
-      "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md",
-      "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+      "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md",
+      "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
       "paths": [
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/SKILL.md",
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-model-adaptation/metadata.json",

src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-profiling.json

@@ -23,8 +23,8 @@
   "sources": [
     {
       "type": "git",
-      "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md",
-      "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+      "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md",
+      "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
       "paths": [
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/SKILL.md",
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-profiling/metadata.json",

src/inferrsi/data/repo_packs/inferrsi/knowledge/ascend/skills/ascend-operator-tuning.json

@@ -24,8 +24,8 @@
   "sources": [
     {
       "type": "git",
-      "url": "https://github.com/InferMatrixLab/InferRSI/blob/7aa3344bf84c42467f43b3a927e1c7d13642bd55/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md",
-      "commit": "7aa3344bf84c42467f43b3a927e1c7d13642bd55",
+      "url": "https://github.com/InferMatrixLab/InferRSI/blob/bb4720992ac2a515adc09b645e1e3cfda47e9d69/src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md",
+      "commit": "bb4720992ac2a515adc09b645e1e3cfda47e9d69",
       "paths": [
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/SKILL.md",
         "src/inferrsi/data/skill_library/hardware/ascend/ascend-operator-tuning/metadata.json",