books/gu-zhenren/exp15/q4a_det_results.json

1098 lines
No EOL
20 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"n_traps": 9,
"seeds": [
0,
1,
2
],
"n_complete_square": 9,
"n_paired_decided": 9,
"fixrate_matrix": {
"flash_raw": {
"marginal": [
1.0,
9
],
"paired": [
1.0,
9
],
"cat": [
1.0,
3
]
},
"pro_raw": {
"marginal": [
0.889,
9
],
"paired": [
0.889,
9
],
"cat": [
1.0,
3
]
},
"flash_glm": {
"marginal": [
0.778,
9
],
"paired": [
0.778,
9
],
"cat": [
1.0,
3
]
},
"pro_glm": {
"marginal": [
0.889,
9
],
"paired": [
0.889,
9
],
"cat": [
1.0,
3
]
}
},
"d5_rule": {
"flash_fail_traps": [],
"n_denominator": 0,
"min_denominator": 3,
"pro_fixes": 0,
"fix_rate": null,
"threshold": 0.5,
"powered": false,
"ratified": null,
"status": "INSUFFICIENT-POWER",
"incomplete_traps": [],
"detail": []
},
"editor_delta_pro": {
"mean_delta": -0.093,
"n": 9,
"editor_breaks": [
{
"id": "c2",
"raw": 1.0,
"glm": 0.5
},
{
"id": "d2",
"raw": 0.333,
"glm": 0.0
}
]
},
"editor_delta_flash": {
"mean_delta": -0.185,
"n": 9,
"editor_breaks": [
{
"id": "c2",
"raw": 1.0,
"glm": 0.0
},
{
"id": "c3",
"raw": 1.0,
"glm": 0.333
}
]
},
"seed_floor": {
"flash_raw": {
"disagree": 0,
"n_multi_decided": 9,
"rate": 0.0
},
"pro_raw": {
"disagree": 1,
"n_multi_decided": 9,
"rate": 0.111
},
"flash_glm": {
"disagree": 1,
"n_multi_decided": 9,
"rate": 0.111
},
"pro_glm": {
"disagree": 1,
"n_multi_decided": 8,
"rate": 0.125
}
},
"coverage": {
"flash_raw": {
"located": 26,
"seen": 27,
"rate": 0.963
},
"pro_raw": {
"located": 26,
"seen": 27,
"rate": 0.963
},
"flash_glm": {
"located": 24,
"seen": 27,
"rate": 0.889
},
"pro_glm": {
"located": 27,
"seen": 27,
"rate": 1.0
}
},
"editor_restoration": {
"flash": {
"restored": [],
"n_restored": 0,
"broke": [
{
"id": "c2",
"seed": 0
},
{
"id": "d2",
"seed": 2
}
],
"n_broke": 2,
"both_absent": 1
},
"pro": {
"restored": [
{
"id": "b2",
"seed": 0
}
],
"n_restored": 1,
"broke": [],
"n_broke": 0,
"both_absent": 0
}
},
"provenance_xcheck": {
"backend_flash_raw": {
"a1": "fail",
"a2": "fix",
"b1": "fix",
"b2": "fix",
"c1": "fail",
"c2": "fix",
"c3": "fix",
"d1": "fix",
"d2": "fix"
},
"exp14b_arm_C": {
"a1": "fail",
"a2": "fix",
"b1": "fix",
"b2": "fix",
"c1": "fix",
"c2": "fix",
"c3": "fail",
"d1": "fix",
"d2": "fix"
}
},
"cogs": {
"by_cell": {
"flash_raw": {
"cost": 0.02431,
"n": 21
},
"flash_glm": {
"cost": 0.20882,
"n": 21
},
"pro_raw": {
"cost": 0.08926,
"n": 22
},
"pro_glm": {
"cost": 0.2192,
"n": 22
},
"DIAG_pro_reasoning": {
"cost": 0.0026,
"n": 1
},
"CHAR_deepseek-v4-flash": {
"cost": 0.0039,
"n": 4
},
"PROBE_deepseek-v4-flash": {
"cost": 0.01198,
"n": 10
},
"PROBE_deepseek-v4-pro": {
"cost": 0.04145,
"n": 10
}
},
"draft_stage_flash": 0.02431,
"draft_stage_pro": 0.08926,
"pro_over_flash_x": 3.67
},
"per_trap": [
{
"id": "a1",
"chunk": "7.0",
"cat_class": true,
"desc": "все знали (двойн.отриц.)",
"cells": {
"flash_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"flash_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 1,
"n_q": 2,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
}
},
"seed_raw": {
"flash_raw": [
"fix",
"fix",
"fix"
],
"pro_raw": [
"fix",
"fix",
"fix"
],
"flash_glm": [
"fix",
"fix",
"fix"
],
"pro_glm": [
"fix",
"?",
"?"
]
},
"seed_located": {
"flash_raw": [
true,
true,
true
],
"pro_raw": [
true,
true,
true
],
"flash_glm": [
true,
true,
true
],
"pro_glm": [
true,
true,
true
]
},
"complete": true,
"paired_decided": true
},
{
"id": "a2",
"chunk": "7.0",
"cat_class": true,
"desc": "все полны зависти (无不)",
"cells": {
"flash_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"flash_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
}
},
"seed_raw": {
"flash_raw": [
"fix",
"fix",
"fix"
],
"pro_raw": [
"fix",
"fix",
"fix"
],
"flash_glm": [
"fix",
"fix",
"fix"
],
"pro_glm": [
"fix",
"fix",
"fix"
]
},
"seed_located": {
"flash_raw": [
true,
true,
true
],
"pro_raw": [
true,
true,
true
],
"flash_glm": [
true,
true,
true
],
"pro_glm": [
true,
true,
true
]
},
"complete": true,
"paired_decided": true
},
{
"id": "b1",
"chunk": "10.1",
"cat_class": false,
"desc": "1/12 & 30%",
"cells": {
"flash_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 2,
"n_q": 1,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"flash_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 2,
"n_q": 1,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
}
},
"seed_raw": {
"flash_raw": [
"fix",
"fix",
"fix"
],
"pro_raw": [
"?",
"fix",
"fix"
],
"flash_glm": [
"fix",
"fix",
"fix"
],
"pro_glm": [
"?",
"fix",
"fix"
]
},
"seed_located": {
"flash_raw": [
true,
true,
true
],
"pro_raw": [
true,
true,
true
],
"flash_glm": [
true,
true,
true
],
"pro_glm": [
true,
true,
true
]
},
"complete": true,
"paired_decided": true
},
{
"id": "b2",
"chunk": "6.0",
"cat_class": false,
"desc": "44%",
"cells": {
"flash_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 2,
"n_q": 1,
"n_present": 3,
"missing": false,
"n_located": 2,
"n_seen": 3
},
"flash_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
}
},
"seed_raw": {
"flash_raw": [
"fix",
"fix",
"fix"
],
"pro_raw": [
"?",
"fix",
"fix"
],
"flash_glm": [
"fix",
"fix",
"fix"
],
"pro_glm": [
"fix",
"fix",
"fix"
]
},
"seed_located": {
"flash_raw": [
true,
true,
true
],
"pro_raw": [
false,
true,
true
],
"flash_glm": [
true,
true,
true
],
"pro_glm": [
true,
true,
true
]
},
"complete": true,
"paired_decided": true
},
{
"id": "c1",
"chunk": "17.0",
"cat_class": true,
"desc": "над людьми (人上之人)",
"cells": {
"flash_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"flash_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
}
},
"seed_raw": {
"flash_raw": [
"fix",
"fix",
"fix"
],
"pro_raw": [
"fix",
"fix",
"fix"
],
"flash_glm": [
"fix",
"fix",
"fix"
],
"pro_glm": [
"fix",
"fix",
"fix"
]
},
"seed_located": {
"flash_raw": [
true,
true,
true
],
"pro_raw": [
true,
true,
true
],
"flash_glm": [
true,
true,
true
],
"pro_glm": [
true,
true,
true
]
},
"complete": true,
"paired_decided": true
},
{
"id": "c2",
"chunk": "9.1",
"cat_class": false,
"desc": "丙=разряд В",
"cells": {
"flash_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 2,
"n_q": 1,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"flash_glm": {
"label": "fail",
"mean": 0.0,
"n_decided": 2,
"n_q": 1,
"n_present": 3,
"missing": false,
"n_located": 2,
"n_seen": 3
},
"pro_glm": {
"label": "fix",
"mean": 0.5,
"n_decided": 2,
"n_q": 1,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
}
},
"seed_raw": {
"flash_raw": [
"?",
"fix",
"fix"
],
"pro_raw": [
"fix",
"fix",
"fix"
],
"flash_glm": [
"?",
"fail",
"fail"
],
"pro_glm": [
"fix",
"?",
"fail"
]
},
"seed_located": {
"flash_raw": [
true,
true,
true
],
"pro_raw": [
true,
true,
true
],
"flash_glm": [
false,
true,
true
],
"pro_glm": [
true,
true,
true
]
},
"complete": true,
"paired_decided": true
},
{
"id": "c3",
"chunk": "16.0",
"cat_class": false,
"desc": "族长=глава, не старейшина",
"cells": {
"flash_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"flash_glm": {
"label": "fail",
"mean": 0.333,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
}
},
"seed_raw": {
"flash_raw": [
"fix",
"fix",
"fix"
],
"pro_raw": [
"fix",
"fix",
"fix"
],
"flash_glm": [
"fail",
"fix",
"fail"
],
"pro_glm": [
"fix",
"fix",
"fix"
]
},
"seed_located": {
"flash_raw": [
true,
true,
true
],
"pro_raw": [
true,
true,
true
],
"flash_glm": [
true,
true,
true
],
"pro_glm": [
true,
true,
true
]
},
"complete": true,
"paired_decided": true
},
{
"id": "d1",
"chunk": "19.0",
"cat_class": false,
"desc": "幸亏…否则 контрфактив",
"cells": {
"flash_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 2,
"n_q": 1,
"n_present": 3,
"missing": false,
"n_located": 2,
"n_seen": 3
},
"pro_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"flash_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 2,
"n_q": 1,
"n_present": 3,
"missing": false,
"n_located": 2,
"n_seen": 3
},
"pro_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
}
},
"seed_raw": {
"flash_raw": [
"fix",
"fix",
"?"
],
"pro_raw": [
"fix",
"fix",
"fix"
],
"flash_glm": [
"fix",
"fix",
"?"
],
"pro_glm": [
"fix",
"fix",
"fix"
]
},
"seed_located": {
"flash_raw": [
true,
true,
false
],
"pro_raw": [
true,
true,
true
],
"flash_glm": [
true,
true,
false
],
"pro_glm": [
true,
true,
true
]
},
"complete": true,
"paired_decided": true
},
{
"id": "d2",
"chunk": "7.0",
"cat_class": false,
"desc": "否则 контрфактив",
"cells": {
"flash_raw": {
"label": "fix",
"mean": 1.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"pro_raw": {
"label": "fail",
"mean": 0.333,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
},
"flash_glm": {
"label": "fix",
"mean": 1.0,
"n_decided": 2,
"n_q": 1,
"n_present": 3,
"missing": false,
"n_located": 2,
"n_seen": 3
},
"pro_glm": {
"label": "fail",
"mean": 0.0,
"n_decided": 3,
"n_q": 0,
"n_present": 3,
"missing": false,
"n_located": 3,
"n_seen": 3
}
},
"seed_raw": {
"flash_raw": [
"fix",
"fix",
"fix"
],
"pro_raw": [
"fail",
"fix",
"fail"
],
"flash_glm": [
"fix",
"fix",
"?"
],
"pro_glm": [
"fail",
"fail",
"fail"
]
},
"seed_located": {
"flash_raw": [
true,
true,
true
],
"pro_raw": [
true,
true,
true
],
"flash_glm": [
true,
true,
false
],
"pro_glm": [
true,
true,
true
]
},
"complete": true,
"paired_decided": true
}
]
}