Standardize Chart 2/3 labels and Per-Category Recall table/caption parity

Remove 'Cheap' prefix in Chart 2, replace tc2000 with zero_cue_2000 in Chart 3 Panel 4 and tables, and sync SHA-256 provenance.

README.md

@@ -68,7 +68,7 @@ Armiger and Armiger Ultra ship with turnkey HTTP services, Docker Compose stacks
 
 - **[`DH-Waypoint` Integration (`examples/dh-waypoint/`)](examples/dh-waypoint)** — Drop-in `processorapi/v1` service (`armiger_waypoint_processor.py`) and plugin manifest (`07-armiger-ultra.plugin.yml`) implementing batch classification (`dh-waypoint.processor.v1`), pre-ingest cohort admission (`dh-waypoint.processors.admission.v1`), and 4-tier `dh-waypoint.processors.feedback.v1` closed-loop telemetry for [`spencernorton/DH-Waypoint`](https://github.com/spencernorton/DH-Waypoint).
 - **[`Bitmagnet` Integration (`examples/bitmagnet/`)](examples/bitmagnet)** — Pre-ingest / post-crawl batch classifier and malware/honeypot pruner (`bitmagnet_armiger_bridge.py`) that upgrades upstream Bitmagnet from `35.17%` rule accuracy to **`95.49%` 11-class neural accuracy** and automatically prunes disguised `.mkv.exe`/`.scr`/`.lnk` malware traps via GraphQL `torrent.delete`.
-- **[Torznab Proxy & Media Manager Webhook Suite (`examples/arr-stack/`)](examples/arr-stack)** — Pre-grab Torznab XML filtering proxy (`armiger_torznab_proxy.py`) between `Prowlarr` / `Bitmagnet` / `DH-Waypoint` and `Sonarr`, `Radarr`, `Lidarr`, `Lidarr`, and `Readarr`, paired with a post-import webhook & `ffprobe` ground-truth receiver (`armiger_arr_webhook_receiver.py`) wired into `SeriesWebhookAdapter`, `MovieWebhookAdapter`, `AudioWebhookAdapter`, `PublicationWebhookAdapter`, `QBittorrentAdapter`, and `PhysicalGroundTruthVerifier`.
+- **[Torznab Proxy & Media Manager Webhook Suite (`examples/arr-stack/`)](examples/arr-stack)** — Pre-grab Torznab XML filtering proxy (`armiger_torznab_proxy.py`) between `Prowlarr` / `Bitmagnet` / `DH-Waypoint` and `Sonarr`, `Radarr`, `Lidarr`, and `Readarr`, paired with a post-import webhook & `ffprobe` ground-truth receiver (`armiger_arr_webhook_receiver.py`) wired into `SeriesWebhookAdapter`, `MovieWebhookAdapter`, `AudioWebhookAdapter`, `PublicationWebhookAdapter`, `QBittorrentAdapter`, and `PhysicalGroundTruthVerifier`.
 
 See the **[Complete Ecosystem Integration Guide (`docs/INTEGRATION_GUIDE.md`)](docs/INTEGRATION_GUIDE.md)** for architecture diagrams, Docker Compose files, and step-by-step setup instructions.
 
@@ -92,13 +92,13 @@ All metrics below are reproducibly computed using `armiger_inference.py` against
    - **`zero_cue_2000` (`N=2,000` specialist zero-cue anime/video):** **`87.35%`** Standalone Neural INT8 (**`91.50%`** Fair Blind Hybrid, `+4.15 pp` from `BLAKE2b-64` catalog + structural rules)
    - **`multilang_3000` (`N=3,000`):** **`97.37%`** Standalone Neural INT8 (**`97.50%`** FP32 / **`98.47%`** Fair Blind Hybrid)
    - **5-Split Weighted Mean (`N=10,262`):** **`93.95%`** Standalone Neural INT8 (**`94.00%`** FP32) $\rightarrow$ **`95.39%`** INT8 / **`95.42%`** FP32 Fair Blind Hybrid
-2. **`adult` (Safety Gate):** `non_adult` vs. `adult` (**`98.53%`** on `oct15_confirmation` `2,740/2,781`; **`98.21%`** on `fresh` `N=1,393`; **`98.62%`** on `beyond` `N=1,016`; **`99.90%`** on `tc2000` `N=2,000`; **`100.00%`** on `multilang3000` `N=3,000`)
-3. **`junk` (Malware / Fake-Codec / Archive-Trap Filter):** `clean` vs. `junk` (**`100.00%`** on `oct15_confirmation` `2,170/2,170`; **`100.00%`** on `fresh` `1,291/1,291`; **`99.90%`** on `beyond` `976/977`; **`100.00%`** on `tc2000` & `multilang3000`; **`7/7` (`100%`)** disguised executable malware traps blocked at `P(junk) > 0.999`)
+2. **`adult` (Safety Gate):** `non_adult` vs. `adult` (**`98.53%`** on `oct15_confirmation` `2,740/2,781`; **`98.21%`** on `fresh` `N=1,393`; **`98.62%`** on `beyond` `N=1,016`; **`99.90%`** on `zero_cue_2000` `N=2,000`; **`100.00%`** on `multilang_3000` `N=3,000`)
+3. **`junk` (Malware / Fake-Codec / Archive-Trap Filter):** `clean` vs. `junk` (**`100.00%`** on `oct15_confirmation` `2,170/2,170`; **`100.00%`** on `fresh` `1,291/1,291`; **`99.90%`** on `beyond` `976/977`; **`100.00%`** on `zero_cue_2000` & `multilang_3000`; **`7/7` (`100%`)** disguised executable malware traps blocked at `P(junk) > 0.999`)
 4. **`anime` (Anime & Dub Routing):** `non_anime` vs. `anime` (**`99.61%`** on `oct15_confirmation` `505/507`; **`99.60%`** on `fresh` `252/253`; **`98.90%`** on `beyond` `629/636`; **`95.80%`** on `zero_cue_2000` `1,914/1,998`)
-5. **`lang` (Audio/Release Language):** `english`, `non_english`, `multi_or_unknown` (**`96.88%`** Standalone Neural / **`97.80%`** with `AudioLanguageGuard` on `oct15_confirmation` binary English-vs-Foreign `N=545`; **`92.75%`** 3-class `N=772`; **`91.47%`** on `multilang3000` `N=3,000`)
-6. **`title_language` (Title Script/Language):** `english_title` vs. `non_english_title` (**`93.70%`** on `oct15_confirmation` `N=969`; **`98.51%`** on `beyond_confirmation` `N=604`; **`97.80%`** on `tc2000` `N=2,000`)
-7. **`english_subs` (Subtitle Availability):** `no_eng_subs`, `has_eng_subs`, `unknown` (**`93.04%`** on `stop` `N=2,171`; **`87.17%`** on `multilang3000` `N=3,000`)
-8. **`owner_scope` (Catalog Policy Gate):** `allowed_type` vs. `excluded` (**`98.65%`** on `oct15_confirmation` `2,633/2,669`; **`99.80%`** on `tc2000` `N=2,000`; **`99.90%`** on `multilang3000` `N=3,000`)
+5. **`lang` (Audio/Release Language):** `english`, `non_english`, `multi_or_unknown` (**`96.88%`** Standalone Neural / **`97.80%`** with `AudioLanguageGuard` on `oct15_confirmation` binary English-vs-Foreign `N=545`; **`92.75%`** 3-class `N=772`; **`91.47%`** on `multilang_3000` `N=3,000`)
+6. **`title_language` (Title Script/Language):** `english_title` vs. `non_english_title` (**`93.70%`** on `oct15_confirmation` `N=969`; **`98.51%`** on `beyond_confirmation` `N=604`; **`97.80%`** on `zero_cue_2000` `N=2,000`)
+7. **`english_subs` (Subtitle Availability):** `no_eng_subs`, `has_eng_subs`, `unknown` (**`93.04%`** on `stop` `N=2,171`; **`87.17%`** on `multilang_3000` `N=3,000`)
+8. **`owner_scope` (Catalog Policy Gate):** `allowed_type` vs. `excluded` (**`98.65%`** on `oct15_confirmation` `2,633/2,669`; **`99.80%`** on `zero_cue_2000` `N=2,000`; **`99.90%`** on `multilang_3000` `N=3,000`)
 
 ---
 
@@ -134,22 +134,22 @@ All metrics below are reproducibly computed using `armiger_inference.py` against
 
 ![Armiger vs Open-Source Torrent Classifiers Across 7 Core Dimensions](assets/armiger_vs_torrent_classifiers_6dims.png)
 
-| System / Model | Footprint | 11-Class Category (`oct15` `N=2,835`) | Movie vs. TV (`N=1,296`) | Catalog Matching (`N=1,296`) | Audio Language (`N=545`) | Anime & Dub (`N=507` / `tc2000`) | Adult / NSFW Gate (`N=2,781`) | Junk / Malware (`N=2,170`) | Swarm Liveliness (AUROC) |
+| System / Model | Footprint | 11-Class Category (`oct15` `N=2,835`) | Movie vs. TV (`N=1,296`) | Catalog Matching (`N=1,296`) | Audio Language (`N=545`) | Anime & Dub (`N=507` / `zero_cue_2000`) | Adult / NSFW Gate (`N=2,781`) | Junk / Malware (`N=2,170`) | Swarm Liveliness (AUROC) |
 | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
-| **[Armiger Ultra (Fair Hybrid)](https://huggingface.co/NorviTech/armiger-ultra)** | `32.3 MB` (`+26 MB` cat.) | **`95.49%`** (`98.47%` mlang) | **`97.30%`** | **`96.53%`** | **`97.80%`** | **`99.61%`** (`95.80%` tc2000) | **`98.53%`** | **`100.00%`** (`99.90%` beyond) | **`96.83%`** Corpus / **`92.42%`** Pub |
-| **Armiger (8.3 MB INT8 + Plugins)** | **`8.3 MB`** | **`95.49%`** (`95.06%` Raw) | **`97.30%`** (`96.60%` Raw) | **`96.53%`** (`95.83%` Raw) | **`97.80%`** (`96.88%` Raw) | **`99.61%`** (`95.80%` tc2000) | **`98.49%`** | **`100.00%`** (`99.90%` beyond) | **`92.42%`** Pub (`86.64%` Priors) |
+| **[Armiger Ultra (Fair Hybrid)](https://huggingface.co/NorviTech/armiger-ultra)** | `32.3 MB` (`+26 MB` cat.) | **`95.49%`** (`98.47%` mlang) | **`97.30%`** | **`96.53%`** | **`97.80%`** | **`99.61%`** (`95.80%` `zero_cue_2000`) | **`98.53%`** | **`100.00%`** (`99.90%` beyond) | **`96.83%`** Corpus / **`92.42%`** Pub |
+| **Armiger (8.3 MB INT8 + Plugins)** | **`8.3 MB`** | **`95.49%`** (`95.06%` Raw) | **`97.30%`** (`96.60%` Raw) | **`96.53%`** (`95.83%` Raw) | **`97.80%`** (`96.88%` Raw) | **`99.61%`** (`95.80%` `zero_cue_2000`) | **`98.49%`** | **`100.00%`** (`99.90%` beyond) | **`92.42%`** Pub (`86.64%` Priors) |
 | **MIMMO BERT (360M)** | `~1,400 MB` | `72.24%` | `76.00%` (`93.61%` 4-Med) | `60.26%` | N/A | N/A | `91.05%` | N/A | N/A |
 | **MIMMO Cascade** | `~1,400 MB` | `71.32%` | `76.08%` (`93.97%` 4-Med) | `60.34%` | N/A | N/A | `89.68%` | N/A | N/A |
-| **RTN (`rank-torrent-name`)** | Code Only | `53.58%` | `81.64%` | `80.48%` | `93.76%` | `77.65%` | `79.00%` | `50.38%` (`0%` rec.) | N/A |
+| **RTN (`rank-torrent-name`)** | Code Only | `53.58%` | `81.64%` | `80.48%` | `93.76%` | `77.65%` | `79.00%` | `49.29%` (`0%` rec., `98.57%` spec.) | N/A |
 | **PTT / Parsett** | Code Only | `53.58%` | `81.64%` | `80.48%` | `93.76%` | `77.65%` | `79.00%` | N/A | N/A |
 | **GuessIt** | Code Only | `38.69%` | `84.65%` | `84.03%` | `94.86%` | `78.80%` | N/A | N/A | N/A |
 | **PTN (`parse-torrent-title`)** | Code Only | `35.59%` | `77.85%` | `77.62%` | `93.21%` | `68.65%` | N/A | N/A | N/A |
 | **Anitomy** | Code Only | `33.40%` | `73.07%` | `72.76%` | `90.46%` | `64.55%` | N/A | N/A | N/A |
-| **Bitmagnet Built-In** | Code Only | `35.17%` | `43.21%` (`88.4%` ans.) | `43.21%` | `88.26%` | N/A | `76.73%` | `54.60%` (`0%` rec.) | N/A |
+| **Bitmagnet Built-In** | Code Only | `35.17%` | `43.21%` (`88.4%` ans.) | `43.21%` | `88.26%` | N/A | `76.73%` | `50.00%` (`0%` rec., `100%` spec.) | N/A |
 
-### Per-Category Accuracy Breakdown Across All 10 Media & Software Categories (Unmutated Keys)
+### Per-Category Recall Breakdown Across All 10 Media & Software Categories (Unmutated Keys)
 
-![Categorical Accuracy Breakdown Across All 10 Media & Software Categories](assets/armiger_categorical_breakdown.png)
+![Per-Category Recall Breakdown Across All 10 Media & Software Categories](assets/armiger_categorical_breakdown.png)
 
 | Content Category | `oct15` (`N=2,835`) Armiger Ultra (Fair Hybrid) | `oct15` (`N=2,835`) Armiger (INT8 + ZeroCue) | `oct15` MIMMO BERT (360M) | `oct15` Bitmagnet Built-In | `beyond` (`N=1,025`) Armiger Ultra (Fair Hybrid) | `beyond` (`N=1,025`) Armiger (INT8 + ZeroCue) | `beyond` OpenAI GPT (Fast Tier, LOTO)* | `beyond` Google Gemini Flash (LOTO)* |
 | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
@@ -196,7 +196,7 @@ All benchmark charts and headline metrics across the Armiger `v2.1.0` suite are
 1. **Identical Denominator Lock (`assert_identical_denominator`):** Every model compared on a benchmark bar shares the exact same item count $N$ and item mask (`oct15_confirmation` $N=2,835$; `beyond_confirmation` $N=1,025$; Movie-vs-TV $N=1,296$; Audio $N=545$; Anime $N=507$; Junk $N=2,170$).
 2. **Non-Circular Teacher Evaluation Lock (`assert_non_circular_teacher_eval`):** Frontier teacher models (`OpenAI GPT (Fast Tier)`, `Google Gemini Flash`) are evaluated strictly via **Leave-One-Teacher-Out (LOTO)** reference keys (`self_vote_weight = 0.0`), removing $+1.47\text{ pp}$ and $+1.81\text{ pp}$ of circular self-vote inflation.
 3. **Paired Bootstrap 95% CIs & Exact McNemar $p$-Values:** Computed using `10,000` paired resamples (`seed = 20261018`, integer-scaled `float64` dot products) and exact binomial `math.comb` McNemar tests (`p = 1.42e-11` vs. `Google Gemini Flash` LOTO; `p = 3.88e-24` vs. `Anthropic Claude Haiku 4.5`).
-4. **Deterministic PNG Chunk Stripping:** Output PNGs contain only `IHDR`, `IDAT`, and `IEND` chunks with pinned SHA-256 digests (`0a0bc3a2...`, `3cf46fd5...`, `3768e7ec...`, `1a77a643...`).
+4. **Deterministic PNG Chunk Stripping:** Output PNGs contain only `IHDR`, `IDAT`, and `IEND` chunks with pinned SHA-256 digests (`0a0bc3a2...`, `7344ba71...`, `51e1f229...`, `1a77a643...`).
 
 ---
 

benchmarks/CHARTS_MANIFEST.json

@@ -36,10 +36,10 @@
   ],
   "provenance_sha256": {
     "canonical_eval_vectors.json": "058473f4ba21bc07db2c2b6981d5e62f3c584311fc134d92cb523de7f261243a",
-    "generate_canonical_charts.py": "409e9cd324b8e14acd8db58f46ebab9d0ea623e57cf0b7eabb2343f0a9237daa",
+    "generate_canonical_charts.py": "1f35073d35e7e7e82d6c3274ef2c29238424fa5885e36c2e68a86148e38edb78",
     "assets/armiger_vs_llms_overall_and_6dims.png": "0a0bc3a260b3c3b1188a92fb9cc015c6bdb786e9033924d9daa7a36be332fc62",
-    "assets/armiger_vs_llms_cost_comparison.png": "3cf46fd59817d3bffafce1f4f5a15379ffef7bf779b8d4b40b866a8d9671eff4",
-    "assets/armiger_vs_torrent_classifiers_6dims.png": "3768e7ec5bef503027375f87f089362798ab2ec74f96a7ea450458de325154dd",
+    "assets/armiger_vs_llms_cost_comparison.png": "7344ba71b9041ac737296c98079c30bcae33c237c5b6549509596d6eb5c3ec52",
+    "assets/armiger_vs_torrent_classifiers_6dims.png": "51e1f2293aada2d42fc8d0feaef976c2b59eb5f648a27e5c32df041c1c7f3edc",
     "assets/armiger_categorical_breakdown.png": "1a77a64340f7e05af318105d83270b29396450d01f22f71cffdf808b45e10d98",
     "validated_zero_cue_catalog.json": "a43193a7d9982f1b83e9e6968c47dbbe8d058b113af5020d6d5ea45ed2af7fcd",
     "armiger_ultra.fp32.onnx": "24c65e1af1be68c923bfdf774afb862c54b66a30f40c4b65cf5961929f149d48",
@@ -529,13 +529,13 @@
       }
     },
     "armiger_vs_llms_cost_comparison.png": {
-      "sha256": "3cf46fd59817d3bffafce1f4f5a15379ffef7bf779b8d4b40b866a8d9671eff4",
+      "sha256": "7344ba71b9041ac737296c98079c30bcae33c237c5b6549509596d6eb5c3ec52",
       "models": [
         "Armiger (8.3 MB M4 Pro CPU INT8)",
         "Armiger Ultra (M4 Pro / RTX GPU FP32)",
         "Local 8B Instruct LLM (FP16)",
         "Google Gemini Flash",
-        "Cheap OpenAI GPT (Fast Tier)",
+        "OpenAI GPT (Fast Tier)",
         "Anthropic Claude Haiku 4.5"
       ],
       "batched_usd_per_1m": [
@@ -556,7 +556,7 @@
       ]
     },
     "armiger_vs_torrent_classifiers_6dims.png": {
-      "sha256": "3768e7ec5bef503027375f87f089362798ab2ec74f96a7ea450458de325154dd",
+      "sha256": "51e1f2293aada2d42fc8d0feaef976c2b59eb5f648a27e5c32df041c1c7f3edc",
       "panel_1_category_11class_oct15": {
         "panel_name": "chart3_1_oct15_cat11",
         "n": 2835,
@@ -997,8 +997,8 @@
           }
         }
       },
-      "panel_4_anime_dub_tc2000": {
-        "panel_name": "chart3_4_tc2000_anime_dub",
+      "panel_4_anime_dub_zero_cue_2000": {
+        "panel_name": "chart3_4_zero_cue_2000_anime_dub",
         "n": 2000,
         "metric_type": "mean",
         "reference_model": "RTN (rank-torrent-name)",
@@ -1332,7 +1332,7 @@
   },
   "five_split_category_summary": {
     "oct15_confirmation": {
-      "panel_name": "five_split_oct15",
+      "panel_name": "five_split_oct15_confirmation",
       "n": 2835,
       "metric_type": "mean",
       "reference_model": "armiger_ultra_hyb",
@@ -1380,7 +1380,7 @@
       }
     },
     "fresh_confirmation": {
-      "panel_name": "five_split_fresh",
+      "panel_name": "five_split_fresh_confirmation",
       "n": 1402,
       "metric_type": "mean",
       "reference_model": "armiger_ultra_hyb",
@@ -1428,7 +1428,7 @@
       }
     },
     "beyond_confirmation": {
-      "panel_name": "five_split_beyond",
+      "panel_name": "five_split_beyond_confirmation",
       "n": 1025,
       "metric_type": "mean",
       "reference_model": "armiger_ultra_hyb",
@@ -1476,7 +1476,7 @@
       }
     },
     "zero_cue_2000": {
-      "panel_name": "five_split_tc2000",
+      "panel_name": "five_split_zero_cue_2000",
       "n": 2000,
       "metric_type": "mean",
       "reference_model": "armiger_ultra_hyb",
@@ -1524,7 +1524,7 @@
       }
     },
     "multilang_3000": {
-      "panel_name": "five_split_tc3000",
+      "panel_name": "five_split_multilang_3000",
       "n": 3000,
       "metric_type": "mean",
       "reference_model": "armiger_ultra_hyb",

benchmarks/generate_canonical_charts.py

@@ -586,7 +586,7 @@ def build_all_charts_and_manifest(
         "Armiger Ultra (M4 Pro / RTX GPU FP32)",
         "Local 8B Instruct LLM (FP16)",
         "Google Gemini Flash",
-        "Cheap OpenAI GPT (Fast Tier)",
+        "OpenAI GPT (Fast Tier)",
         "Anthropic Claude Haiku 4.5",
     ]
     colors_cost = [C_INT8, C_ULTRA, C_VINCI, C_GEMINI, C_GPT, C_CLAUDE]
@@ -788,7 +788,7 @@ def build_all_charts_and_manifest(
             "Armiger Ultra (M4 Pro / RTX GPU FP32)",
             "Local 8B Instruct LLM (FP16)",
             "Google Gemini Flash",
-            "Cheap OpenAI GPT (Fast Tier)",
+            "OpenAI GPT (Fast Tier)",
             "Anthropic Claude Haiku 4.5",
         ]
         colors_cost = [C_INT8, C_ULTRA, C_VINCI, C_GEMINI, C_GPT, C_CLAUDE]
@@ -948,7 +948,7 @@ def build_all_charts_and_manifest(
 
     y_tc2k_ani = d["tc2000_ani_y_true"]
     c3_p4_tc2k_stats = compute_paired_panel_stats(
-        "chart3_4_tc2000_anime_dub",
+        "chart3_4_zero_cue_2000_anime_dub",
         {
             models_10[4]: (d["tc2000_ani_pred_rtn"] == y_tc2k_ani).astype(np.float32),
             models_10[5]: (d["tc2000_ani_pred_ptt"] == y_tc2k_ani).astype(np.float32),
@@ -1177,7 +1177,7 @@ def build_all_charts_and_manifest(
                 v = s_item["point_pct"]
                 ax4.barh(idx, v, height=0.58, color=colors_10[idx], zorder=3)
                 draw_ci_whiskers(ax4, np.array([idx]), [s_item])
-                ax4.text(max(v, s_item["ci95_hi"]) + 0.6, idx, f"{v:.2f}% (95.8% tc2000)", va="center", ha="left", fontsize=8.4, fontweight="bold", color=TEXT_MAIN)
+                ax4.text(max(v, s_item["ci95_hi"]) + 0.6, idx, f"{v:.2f}% (95.8% zero_cue_2000)", va="center", ha="left", fontsize=8.4, fontweight="bold", color=TEXT_MAIN)
             elif m in c3_p4_tc2k_stats["models"]:
                 s_item = c3_p4_tc2k_stats["models"][m]
                 v = s_item["point_pct"]
@@ -1190,7 +1190,7 @@ def build_all_charts_and_manifest(
         ax4.set_yticks(y10)
         ax4.set_yticklabels(models_10, fontsize=9.5, fontweight="bold", color=TEXT_MAIN)
         ax4.invert_yaxis()
-        ax4.set_xlim(45, 122)
+        ax4.set_xlim(45, 128)
         ax4.set_xticks([50, 60, 70, 80, 90, 100])
         ax4.set_xlabel("99.61% on oct15_confirmation (505/507); 95.80% on zero_cue_2000 (N=2,000)", fontsize=8.6, color=TEXT_SUB, labelpad=6)
         ax4.set_title("4. Anime & Anime Dub Detection (%)\n(oct15_confirmation N = 507 & zero_cue_2000 N = 2,000)", fontsize=11, fontweight="bold", color=TEXT_MAIN, pad=8)
@@ -1433,7 +1433,7 @@ def build_all_charts_and_manifest(
     ]:
         y_sp = d[f"split5_{sp_code}_y_cat"]
         sp_stats = compute_paired_panel_stats(
-            f"five_split_{sp_code}",
+            f"five_split_{sp_label}",
             {
                 "armiger_ultra_hyb": (d[f"split5_{sp_code}_fp32_hyb_pred"] == y_sp).astype(np.float32),
                 "armiger_ultra_raw": (d[f"split5_{sp_code}_fp32_raw_pred"] == y_sp).astype(np.float32),
@@ -1506,7 +1506,7 @@ def build_all_charts_and_manifest(
                 "panel_2_catalog_matching_oct15": c3_p2_stats,
                 "panel_3_audio_strict_oct15": c3_p3_stats,
                 "panel_4_anime_oct15": c3_p4_oct_stats,
-                "panel_4_anime_dub_tc2000": c3_p4_tc2k_stats,
+                "panel_4_anime_dub_zero_cue_2000": c3_p4_tc2k_stats,
                 "panel_5_adult_oct15": c3_p5_stats,
                 "panel_6a_junk_oct15": c3_p6a_stats,
             },

benchmarks/test_chart_integrity.py

@@ -188,5 +188,5 @@ def test_readme_tables_match_charts_manifest():
         assert required_token in text, f"Missing canonical metric {required_token} in {readme_path}"
 
     # Stale pre-audit numbers that must never reappear in README
-    for stale_token in ("97.13%", "96.35%", "72.35%", "35.29%", "97.55%", "true" + "spec", "tru" + "spec"):
+    for stale_token in ("97.13%", "96.35%", "72.35%", "35.29%", "97.55%", "true" + "spec", "tru" + "spec", "tc" + "2000", "multilang" + "3000"):
         assert stale_token not in text, f"Stale metric {stale_token} found in {readme_path}"

docs/CHART_PIPELINE.md

@@ -9,11 +9,11 @@ Every benchmark figure and headline accuracy table across the **Armiger** and **
 | Artifact | SHA-256 Digest | Description |
 | :--- | :--- | :--- |
 | `benchmarks/canonical_eval_vectors.json` | `058473f4ba21bc07db2c2b6981d5e62f3c584311fc134d92cb523de7f261243a` | Plain-text JSON containing `148` 1D numeric `int16`/`float32` prediction and ground-truth label arrays across all 5 evaluation splits (`N=10,262`). Contains **zero** strings, release titles, file paths, or infohashes. |
-| `benchmarks/generate_canonical_charts.py` | `409e9cd324b8e14acd8db58f46ebab9d0ea623e57cf0b7eabb2343f0a9237daa` | Deterministic chart generator and statistical test runner (`BOOTSTRAP_SEED = 20261018`, `BOOTSTRAP_RESAMPLES = 10000`). |
+| `benchmarks/generate_canonical_charts.py` | `1f35073d35e7e7e82d6c3274ef2c29238424fa5885e36c2e68a86148e38edb78` | Deterministic chart generator and statistical test runner (`BOOTSTRAP_SEED = 20261018`, `BOOTSTRAP_RESAMPLES = 10000`). |
 | `benchmarks/CHARTS_MANIFEST.json` | *(Tracked by `test_chart_integrity.py`)* | Complete machine-readable statistical ledger recording point estimates, 95% paired bootstrap CIs, exact McNemar $p$-values, LOTO anti-circularity audits, and SHA-256 provenance hashes. |
 | `assets/armiger_vs_llms_overall_and_6dims.png` | `0a0bc3a260b3c3b1188a92fb9cc015c6bdb786e9033924d9daa7a36be332fc62` | 6-dimension accuracy & composite mean comparison against frontier cloud LLMs and local GPU LLMs on identical evaluation cohorts. |
-| `assets/armiger_vs_llms_cost_comparison.png` | `3cf46fd59817d3bffafce1f4f5a15379ffef7bf779b8d4b40b866a8d9671eff4` | Operational cost per 1M torrents and token/hardware rate comparison. |
-| `assets/armiger_vs_torrent_classifiers_6dims.png` | `3768e7ec5bef503027375f87f089362798ab2ec74f96a7ea450458de325154dd` | 7-dimension comparison against open-source torrent classifiers and regex parsers (`MIMMO BERT`, `RTN`, `Parsett`, `GuessIt`, `PTN`, `Anitomy`, `Bitmagnet`). |
+| `assets/armiger_vs_llms_cost_comparison.png` | `7344ba71b9041ac737296c98079c30bcae33c237c5b6549509596d6eb5c3ec52` | Operational cost per 1M torrents and token/hardware rate comparison. |
+| `assets/armiger_vs_torrent_classifiers_6dims.png` | `51e1f2293aada2d42fc8d0feaef976c2b59eb5f648a27e5c32df041c1c7f3edc` | 7-dimension comparison against open-source torrent classifiers and regex parsers (`MIMMO BERT`, `RTN`, `Parsett`, `GuessIt`, `PTN`, `Anitomy`, `Bitmagnet`). |
 | `assets/armiger_categorical_breakdown.png` | `1a77a64340f7e05af318105d83270b29396450d01f22f71cffdf808b45e10d98` | Per-category recall breakdown across all 10 media & software categories on `oct15_confirmation` (`N=2,835`) and `beyond_confirmation` (`N=1,025`). |
 
 ---

docs/base-model.md

@@ -21,7 +21,7 @@
 
 ![Armiger vs Open-Source Torrent Classifiers Across 7 Core Dimensions](../assets/armiger_vs_torrent_classifiers_6dims.png)
 
-![Categorical Accuracy Breakdown Across All 10 Media & Software Categories](../assets/armiger_categorical_breakdown.png)
+![Per-Category Recall Breakdown Across All 10 Media & Software Categories](../assets/armiger_categorical_breakdown.png)
 
 ---