Research-Stack/shared-data/pist_route_repair_v11_benchmark.json

850 lines
No EOL
19 KiB
JSON

{
"n": 28,
"recovered": 0,
"partial_improvement": 0,
"avg_delta": 0.0,
"failure_session_id": "a89baf86-3536-4453-8e2c-7c66d54cf389",
"combined_session_id": "a4a0eb20-93fe-413e-8e0b-50334bb778d8",
"results": [
{
"name": "rw_missing_dir_1",
"obstruction": "missing_rewrite_direction",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "rw_missing_dir_2",
"obstruction": "missing_rewrite_direction",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "rw_missing_dir_3",
"obstruction": "missing_rewrite_direction",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "rw_missing_dir_4",
"obstruction": "missing_rewrite_direction",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "rw_missing_dir_5",
"obstruction": "missing_rewrite_direction",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "rw_missing_dir_6",
"obstruction": "missing_rewrite_direction",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "rw_missing_dir_7",
"obstruction": "missing_rewrite_direction",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "missing_assume_1",
"obstruction": "missing_assumption_bridge",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "missing_assume_2",
"obstruction": "missing_assumption_bridge",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "missing_assume_3",
"obstruction": "missing_assumption_bridge",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "missing_assume_4",
"obstruction": "missing_assumption_bridge",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "missing_assume_5",
"obstruction": "missing_assumption_bridge",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "missing_assume_6",
"obstruction": "missing_assumption_bridge",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "missing_assume_7",
"obstruction": "missing_assumption_bridge",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [P]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 P]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [P]",
"delta": 0,
"ok": false
}
},
{
"name": "arith_gap_1",
"obstruction": "arithmetic_gap",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "arith_gap_2",
"obstruction": "arithmetic_gap",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "arith_gap_3",
"obstruction": "arithmetic_gap",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "arith_gap_4",
"obstruction": "arithmetic_gap",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "arith_gap_5",
"obstruction": "arithmetic_gap",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "arith_gap_6",
"obstruction": "arithmetic_gap",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [x]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 x]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [x]",
"delta": 0,
"ok": false
}
},
{
"name": "arith_gap_8",
"obstruction": "arithmetic_gap",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [a]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 a]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [a]",
"delta": 0,
"ok": false
}
},
{
"name": "arith_gap_9",
"obstruction": "arithmetic_gap",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [x]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 x]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [x]",
"delta": 0,
"ok": false
}
},
{
"name": "case_split_1",
"obstruction": "case_split_missing",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "case_split_2",
"obstruction": "case_split_missing",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "case_split_3",
"obstruction": "case_split_missing",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "case_split_4",
"obstruction": "case_split_missing",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "case_split_5",
"obstruction": "case_split_missing",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
},
{
"name": "case_split_6",
"obstruction": "case_split_missing",
"initial_status": "failed",
"predicted_family": "rewrite",
"recovered": false,
"best_delta": 0,
"partial_improvement": false,
"attempts": [
{
"attempt": 1,
"patch": "rw [A]",
"family": "rewrite",
"ok": false,
"delta": 0
},
{
"attempt": 2,
"patch": "rw [\u2190 A]",
"family": "rewrite",
"ok": false,
"delta": 0
}
],
"best_attempt": {
"patch": "rw [A]",
"delta": 0,
"ok": false
}
}
]
}