loop-benchmarking

commit f801efc9b7f7880049fdeeeed53d55f0ecae5ecc
parent 2fae566a4db8aae4b68eb9a4ff587a6a8e4245a2
Author: Brian Graham <brian@buildingbetterteams.de>
Date:   Thu, 16 Apr 2026 09:54:00 +0200

Add human trial labels for 4 calibration runs

Covers qwen-3.6-plus, haiku-4.5, opus-4.6, glm-5.1 (each with
strat=usub or strat=none). All four are reported playable by the
human tester but the bot currently scores them near zero because
renderer detection fails (renderer=unknown, grid_detected=false),
so aggregate bot-vs-human agreement drops to 47.6%.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Diffstat:
M
tasks/tetris/eval/gameplay-bot/calibration/2763232d.json
 | 
46
+++++++++++++++++++++++-----------------------
M
tasks/tetris/eval/gameplay-bot/calibration/5ae88633.json
 | 
39
+++++++++++++++++++--------------------
M
tasks/tetris/eval/gameplay-bot/calibration/6f157de1.json
 | 
46
+++++++++++++++++++++++-----------------------
M
tasks/tetris/eval/gameplay-bot/calibration/7c167ef9.json
 | 
44
++++++++++++++++++++++----------------------

4 files changed, 87 insertions(+), 88 deletions(-)
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/2763232d.json b/tasks/tetris/eval/gameplay-bot/calibration/2763232d.json
@@ -3,33 +3,34 @@
   "short_id": "2763232d",
   "label": "Calibration (qwen-3.6-plus, en)",
   "notes": "",
-  "human_tested_at": "",
+  "human_tested_at": "2026-04-16",
   "human_tests": {
-    "game_loads": null,
-    "game_starts": null,
-    "auto_drop": null,
-    "move_left": null,
-    "move_right": null,
-    "move_down": null,
-    "rotate": null,
-    "hard_drop": null,
+    "game_loads": true,
+    "game_starts": true,
+    "auto_drop": true,
+    "move_left": true,
+    "move_right": true,
+    "move_down": true,
+    "rotate": true,
+    "hard_drop": true,
     "all_pieces_rotate": null,
-    "piece_locks": null,
-    "new_piece_spawns": null,
-    "multiple_pieces": null,
-    "line_clear": null,
+    "piece_locks": true,
+    "new_piece_spawns": true,
+    "multiple_pieces": true,
+    "line_clear": true,
     "score_increases_on_clear": null,
     "score_element_visible": null,
-    "game_over": null,
-    "playable_30s": null,
-    "multi_line_clear": null,
+    "game_over": true,
+    "playable_30s": true,
+    "multi_line_clear": true,
     "score_scaling": null,
     "level_progression": null,
     "speed_progression": null,
-    "next_piece_preview": null,
-    "game_over_display": null,
-    "counter_clockwise_rotation": null,
-    "soft_drop_distinct": null,
-    "rendering_clean": null
+    "next_piece_preview": true,
+    "game_over_display": true,
+    "counter_clockwise_rotation": true,
+    "soft_drop_distinct": true,
+    "rendering_clean": null,
+    "score_changes": true
   }
-}
-\ No newline at end of file
+}
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/5ae88633.json b/tasks/tetris/eval/gameplay-bot/calibration/5ae88633.json
@@ -3,33 +3,33 @@
   "short_id": "5ae88633",
   "label": "Calibration (haiku-4.5, en)",
   "notes": "",
-  "human_tested_at": "",
+  "human_tested_at": "2026-04-16",
   "human_tests": {
-    "game_loads": null,
-    "game_starts": null,
-    "auto_drop": null,
-    "move_left": null,
-    "move_right": null,
-    "move_down": null,
-    "rotate": null,
-    "hard_drop": null,
-    "all_pieces_rotate": null,
-    "piece_locks": null,
-    "new_piece_spawns": null,
-    "multiple_pieces": null,
-    "line_clear": null,
+    "game_loads": true,
+    "game_starts": true,
+    "auto_drop": false,
+    "move_left": true,
+    "move_right": true,
+    "move_down": true,
+    "rotate": true,
+    "hard_drop": true,
+    "all_pieces_rotate": true,
+    "piece_locks": true,
+    "new_piece_spawns": true,
+    "multiple_pieces": true,
+    "line_clear": true,
     "score_increases_on_clear": null,
     "score_element_visible": null,
-    "game_over": null,
-    "playable_30s": null,
+    "game_over": true,
+    "playable_30s": true,
     "multi_line_clear": null,
     "score_scaling": null,
     "level_progression": null,
     "speed_progression": null,
-    "next_piece_preview": null,
-    "game_over_display": null,
+    "next_piece_preview": true,
+    "game_over_display": true,
     "counter_clockwise_rotation": null,
     "soft_drop_distinct": null,
     "rendering_clean": null
   }
-}
-\ No newline at end of file
+}
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/6f157de1.json b/tasks/tetris/eval/gameplay-bot/calibration/6f157de1.json
@@ -3,33 +3,34 @@
   "short_id": "6f157de1",
   "label": "Calibration (opus-4.6, en)",
   "notes": "",
-  "human_tested_at": "",
+  "human_tested_at": "2026-04-16",
   "human_tests": {
-    "game_loads": null,
-    "game_starts": null,
-    "auto_drop": null,
-    "move_left": null,
-    "move_right": null,
-    "move_down": null,
-    "rotate": null,
-    "hard_drop": null,
-    "all_pieces_rotate": null,
-    "piece_locks": null,
-    "new_piece_spawns": null,
-    "multiple_pieces": null,
-    "line_clear": null,
+    "game_loads": true,
+    "game_starts": true,
+    "auto_drop": true,
+    "move_left": true,
+    "move_right": true,
+    "move_down": true,
+    "rotate": true,
+    "hard_drop": true,
+    "all_pieces_rotate": true,
+    "piece_locks": true,
+    "new_piece_spawns": true,
+    "multiple_pieces": true,
+    "line_clear": true,
     "score_increases_on_clear": null,
     "score_element_visible": null,
-    "game_over": null,
-    "playable_30s": null,
-    "multi_line_clear": null,
+    "game_over": true,
+    "playable_30s": true,
+    "multi_line_clear": true,
     "score_scaling": null,
     "level_progression": null,
     "speed_progression": null,
-    "next_piece_preview": null,
-    "game_over_display": null,
-    "counter_clockwise_rotation": null,
+    "next_piece_preview": true,
+    "game_over_display": true,
+    "counter_clockwise_rotation": true,
     "soft_drop_distinct": null,
-    "rendering_clean": null
+    "rendering_clean": null,
+    "score_changes": true
   }
-}
-\ No newline at end of file
+}
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/7c167ef9.json b/tasks/tetris/eval/gameplay-bot/calibration/7c167ef9.json
@@ -3,33 +3,34 @@
   "short_id": "7c167ef9",
   "label": "Calibration (glm-5.1, en)",
   "notes": "",
-  "human_tested_at": "",
+  "human_tested_at": "2026-04-16",
   "human_tests": {
-    "game_loads": null,
-    "game_starts": null,
-    "auto_drop": null,
-    "move_left": null,
-    "move_right": null,
-    "move_down": null,
-    "rotate": null,
-    "hard_drop": null,
-    "all_pieces_rotate": null,
-    "piece_locks": null,
-    "new_piece_spawns": null,
-    "multiple_pieces": null,
-    "line_clear": null,
+    "game_loads": true,
+    "game_starts": true,
+    "auto_drop": true,
+    "move_left": true,
+    "move_right": true,
+    "move_down": true,
+    "rotate": true,
+    "hard_drop": true,
+    "all_pieces_rotate": true,
+    "piece_locks": true,
+    "new_piece_spawns": true,
+    "multiple_pieces": true,
+    "line_clear": true,
     "score_increases_on_clear": null,
     "score_element_visible": null,
-    "game_over": null,
-    "playable_30s": null,
-    "multi_line_clear": null,
+    "game_over": true,
+    "playable_30s": true,
+    "multi_line_clear": true,
     "score_scaling": null,
     "level_progression": null,
     "speed_progression": null,
-    "next_piece_preview": null,
-    "game_over_display": null,
+    "next_piece_preview": true,
+    "game_over_display": true,
     "counter_clockwise_rotation": null,
     "soft_drop_distinct": null,
-    "rendering_clean": null
+    "rendering_clean": null,
+    "score_changes": true
   }
-}
-\ No newline at end of file
+}