XY-899: [ELF benchmark vNext P3] Add qmd and OpenViking strength-profile benchmarks

README.md

@@ -153,12 +153,15 @@ provider-backed ELF evidence was required.
   jobs across 11 suites, 36 pass, 0 incomplete, 2 blocked, 0 wrong-result,
   0 not-encoded, and 0 unsupported-claim results. The remaining non-pass jobs are
   production-ops operator boundaries, not hidden benchmark wins.
-- Full-suite live real-world adapter sweep after XY-880: ELF and qmd now emit
+- Full-suite live real-world adapter sweep after XY-899: ELF and qmd emit
   Docker-isolated `live_real_world` records for all 38 encoded jobs across 11 suites
   through `cargo make real-world-memory-live-adapters`. Both keep the original
   targeted `work_resume`, `retrieval`, and `project_decisions` slice passing, but the
-  full sweep is not a full-suite pass: each adapter reports 18 pass, 5 wrong_result,
-  1 incomplete, 2 blocked, and 12 not_encoded jobs.
+  full sweep is not a full-suite pass. The fresh ELF sweep reports 18 pass,
+  5 wrong_result, 2 blocked, and 13 not_encoded jobs. The fresh qmd sweep reports
+  17 pass, 6 wrong_result, 2 blocked, and 13 not_encoded jobs. The difference is the
+  delete/TTL tombstone case; qmd remains the local retrieval-debug UX reference, and
+  no broad ELF-over-qmd claim is allowed.
 - Expanded adapter-pack coverage after XY-834: the real-world external adapter
   manifest now includes `research_gate` records for RAGFlow, LightRAG, GraphRAG,
   Graphiti/Zep, Letta, LangGraph, nanograph, llm-wiki, gbrain, and deeper
@@ -191,6 +194,7 @@ Detailed evidence and interpretation:
 - [Real-World Comparison Report - June 10, 2026](docs/guide/benchmarking/2026-06-10-real-world-comparison-report.md)
 - [Live Real-World Adapter Sweep Report - June 10, 2026](docs/guide/benchmarking/2026-06-10-live-real-world-sweep-report.md)
 - [Post-Adapter Production Adoption Refresh - June 10, 2026](docs/guide/benchmarking/2026-06-10-production-adoption-refresh.md)
+- [qmd and OpenViking Strength-Profile Report - June 11, 2026](docs/guide/benchmarking/2026-06-11-qmd-openviking-strength-profile-report.md)
 - [Graph/RAG Scored Smoke Adapter Report - June 11, 2026](docs/guide/benchmarking/2026-06-11-graph-rag-scored-smoke-adapter-report.md)
 - [Live Baseline Benchmark Runbook](docs/guide/benchmarking/live_baseline_benchmark.md)
 - [Single-User Production Runbook](docs/guide/single_user_production.md)
@@ -204,7 +208,7 @@ Detailed evidence and interpretation:
   live sweep, but that sweep still contains typed non-pass states and is not
   full-suite parity.
 
-Evidence-backed position after the June 10 real-world report:
+Evidence-backed position after the June 11 real-world reports:
 
 - ELF is better evidenced than the tested alternatives on evidence-bound writes,
   deterministic ingestion boundaries, Postgres source-of-truth plus rebuildable Qdrant
@@ -276,7 +280,7 @@ Detailed comparison, mechanism-level analysis, and source map:
 - [RAG/Graph Adapter Feasibility Research Run](docs/research/2026-06-10-xy-882-rag-graph-adapter-feasibility.json)
 
 Latest real-world benchmark report: June 11, 2026. Latest external research refresh:
-June 10, 2026.
+June 11, 2026.
 
 ## Documentation
 

apps/elf-eval/fixtures/real_world_external_adapters/memory_projects_manifest.json

@@ -290,7 +290,7 @@
       },
       "result": {
         "status": "pass",
-        "evidence": "The current evidence is same-corpus live-baseline evidence only; no real_world_job qmd adapter is encoded yet.",
+        "evidence": "This live_baseline_only record is same-corpus evidence only; cite qmd_live_real_world for the full live real-world sweep.",
         "artifact": "docs/guide/benchmarking/live_baseline_benchmark.md"
       },
       "capabilities": [
@@ -314,7 +314,7 @@
         {
           "suite_id": "retrieval",
           "status": "not_encoded",
-          "evidence": "qmd is a retrieval-debug reference, but no real_world_job retrieval adapter run is encoded."
+          "evidence": "This live_baseline_only record does not execute real_world_job retrieval prompts; cite qmd_live_real_world for the live retrieval adapter run."
         },
         {
           "suite_id": "memory_evolution",
@@ -425,7 +425,7 @@
         {
           "suite_id": "memory_evolution",
           "status": "wrong_result",
-          "evidence": "qmd passed the delete/TTL case but failed five current-versus-historical conflict jobs because retrieval-backed answers did not provide the required historical conflict evidence links."
+          "evidence": "qmd failed all six memory-evolution jobs in the fresh June 11 diagnostic, including the delete/TTL tombstone job where qmd retrieved only the current plan and missed the tombstone evidence."
         },
         {
           "suite_id": "consolidation",
@@ -1036,11 +1036,12 @@
       },
       "run": {
         "status": "not_encoded",
-        "evidence": "No expanded qmd stress or real_world_job deep-profile artifact is checked in for this adapter-pack gate."
+        "evidence": "The XY-899 strength-profile report is checked in, but no new live qmd deep-profile adapter artifact is claimed from it."
       },
       "result": {
         "status": "not_encoded",
-        "evidence": "qmd deep retrieval-debug evidence remains a planned profile, not a new pass claim."
+        "evidence": "The XY-899 report records qmd scenario-level retrieval/debug/replay outcomes and wrong-result diagnosis taxonomy, while expansion/fusion/rerank scoring remains not_encoded.",
+        "artifact": "docs/research/2026-06-11-qmd-openviking-strength-profile-report.json"
       },
       "capabilities": [
         {
@@ -1051,7 +1052,7 @@
         {
           "capability": "real_world_job_adapter",
           "status": "not_encoded",
-          "evidence": "The qmd live real-world slice covers representative jobs only; expanded retrieval-debug suites need their own materialized adapter run."
+          "evidence": "The qmd live real-world sweep covers the current encoded fixture corpus; expanded retrieval-debug strength suites still need their own materialized adapter run."
         },
         {
           "capability": "host_global_install_boundary",
@@ -1107,7 +1108,7 @@
     {
       "adapter_id": "openviking_deep_profile_gate",
       "project": "OpenViking",
-      "adapter_kind": "docker_local_embed_deep_profile_gate",
+      "adapter_kind": "docker_local_embed_context_trajectory_gate",
       "evidence_class": "research_gate",
       "docker_default": true,
       "host_global_installs_required": false,
@@ -1120,11 +1121,12 @@
       },
       "run": {
         "status": "not_encoded",
-        "evidence": "The adapter cannot fairly exercise hierarchical trajectory behavior until same-corpus add_resource/find returns evidence-bearing results."
+        "evidence": "The XY-899 strength-profile report records staged retrieval, hierarchy selection, recursive/context expansion, and missed-term evidence as typed not_tested or wrong_result states; no new live trajectory adapter artifact is claimed."
       },
       "result": {
         "status": "not_encoded",
-        "evidence": "No OpenViking deep context-trajectory result is claimed from the current wrong-result smoke run."
+        "evidence": "No OpenViking deep context-trajectory result is claimed from the current wrong-result smoke run; the XY-899 report preserves the trajectory surfaces as not_tested.",
+        "artifact": "docs/research/2026-06-11-qmd-openviking-strength-profile-report.json"
       },
       "capabilities": [
         {
@@ -1135,7 +1137,7 @@
         {
           "capability": "hierarchical_context_trajectory",
           "status": "not_encoded",
-          "evidence": "Stage trajectory scoring is not encoded until setup reaches runnable OpenViking APIs."
+          "evidence": "Stage trajectory scoring remains not encoded until the smoke adapter returns evidence-bearing same-corpus output instead of the current wrong_result missed-term evidence."
         },
         {
           "capability": "host_global_install_boundary",