Review: 9 random high-score checks; easy candidates list
This commit is contained in:
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"decision": "accept",
|
"decision": "accept",
|
||||||
"note": "Screened: rules map to tests, mutation ok, no craft hints. H: real gap. K: names kept.",
|
"note": "Random high-score re-check (2026-10-03): rules map to tests, no craft hints, no leak; mutation ok.",
|
||||||
"by": "Claude",
|
"by": "Claude",
|
||||||
"date": "2026-10-03",
|
"date": "2026-10-03",
|
||||||
"failed_checks": {}
|
"failed_checks": {}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"decision": "accept",
|
"decision": "accept",
|
||||||
"note": "Screened: rules map to tests, mutation ok, no craft hints. H: real gap. K: names kept.",
|
"note": "Random high-score re-check (2026-10-03): rules map to tests, no craft hints, no leak; mutation ok.",
|
||||||
"by": "Claude",
|
"by": "Claude",
|
||||||
"date": "2026-10-03",
|
"date": "2026-10-03",
|
||||||
"failed_checks": {}
|
"failed_checks": {}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"decision": "accept",
|
"decision": "accept",
|
||||||
"note": "Screened: rules map to tests, mutation ok, no craft hints. H: real gap. K: names kept.",
|
"note": "Random high-score re-check (2026-10-03): rules map to tests, no craft hints, no leak; mutation ok.",
|
||||||
"by": "Claude",
|
"by": "Claude",
|
||||||
"date": "2026-10-03",
|
"date": "2026-10-03",
|
||||||
"failed_checks": {}
|
"failed_checks": {}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"decision": "accept",
|
"decision": "accept",
|
||||||
"note": "Screened: rules map to tests, mutation ok, no craft hints. H: real gap. K: names kept.",
|
"note": "Random high-score re-check (2026-10-03): rules map to tests, no craft hints, no leak; mutation ok.",
|
||||||
"by": "Claude",
|
"by": "Claude",
|
||||||
"date": "2026-10-03",
|
"date": "2026-10-03",
|
||||||
"failed_checks": {}
|
"failed_checks": {}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"decision": "accept",
|
"decision": "accept",
|
||||||
"note": "Screened: rules map to tests, mutation ok, no craft hints. H: real gap. K: names kept.",
|
"note": "Random high-score re-check (2026-10-03): rules map to tests, no craft hints, no leak; mutation ok.",
|
||||||
"by": "Claude",
|
"by": "Claude",
|
||||||
"date": "2026-10-03",
|
"date": "2026-10-03",
|
||||||
"failed_checks": {}
|
"failed_checks": {}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"decision": "accept",
|
"decision": "accept",
|
||||||
"note": "Screened: rules map to tests, mutation ok, no craft hints. H: real gap. K: names kept.",
|
"note": "Random high-score re-check (2026-10-03): rules map to tests, no craft hints, no leak; mutation ok.",
|
||||||
"by": "Claude",
|
"by": "Claude",
|
||||||
"date": "2026-10-03",
|
"date": "2026-10-03",
|
||||||
"failed_checks": {}
|
"failed_checks": {}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"decision": "accept",
|
"decision": "accept",
|
||||||
"note": "Screened: rules map to tests, mutation ok, no craft hints. H: real gap. K: names kept.",
|
"note": "Random high-score re-check (2026-10-03): rules map to tests, no craft hints, no leak; mutation ok.",
|
||||||
"by": "Claude",
|
"by": "Claude",
|
||||||
"date": "2026-10-03",
|
"date": "2026-10-03",
|
||||||
"failed_checks": {}
|
"failed_checks": {}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"decision": "accept",
|
"decision": "accept",
|
||||||
"note": "Survived mutant: round dec +1, equivalent (result field has fewer decimals).",
|
"note": "Random high-score re-check (2026-10-03): rules map to tests, no craft hints, no leak; mutation ok.",
|
||||||
"by": "Claude",
|
"by": "Claude",
|
||||||
"date": "2026-10-03",
|
"date": "2026-10-03",
|
||||||
"failed_checks": {}
|
"failed_checks": {}
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"decision": "accept",
|
"decision": "accept",
|
||||||
"note": "Survived mutant: round dec +1, equivalent (result field has fewer decimals).",
|
"note": "Random high-score re-check (2026-10-03): rules map to tests, no craft hints, no leak; mutation ok.",
|
||||||
"by": "Claude",
|
"by": "Claude",
|
||||||
"date": "2026-10-03",
|
"date": "2026-10-03",
|
||||||
"failed_checks": {}
|
"failed_checks": {}
|
||||||
|
|||||||
45
tasks_gen/eval/easy_candidates.json
Normal file
45
tasks_gen/eval/easy_candidates.json
Normal file
@@ -0,0 +1,45 @@
|
|||||||
|
{
|
||||||
|
"rule": "DeepSeek (budget 60) score >= 95 and tool_calls <= 20, outcome implement; candidate only until the Qwen baseline confirms",
|
||||||
|
"date": "2026-10-03",
|
||||||
|
"tasks": [
|
||||||
|
"G0003",
|
||||||
|
"G0004",
|
||||||
|
"G0007",
|
||||||
|
"G0008",
|
||||||
|
"G0010",
|
||||||
|
"G0100",
|
||||||
|
"G0101",
|
||||||
|
"G0103",
|
||||||
|
"G0104",
|
||||||
|
"G0113",
|
||||||
|
"G0114",
|
||||||
|
"G0115",
|
||||||
|
"G0116",
|
||||||
|
"G0117",
|
||||||
|
"G0118",
|
||||||
|
"G0120",
|
||||||
|
"G0127",
|
||||||
|
"G0129",
|
||||||
|
"G0130",
|
||||||
|
"G0135",
|
||||||
|
"G0136",
|
||||||
|
"G0137",
|
||||||
|
"G0138",
|
||||||
|
"G0139",
|
||||||
|
"G0141",
|
||||||
|
"G0142",
|
||||||
|
"G0148",
|
||||||
|
"G0149",
|
||||||
|
"G0150",
|
||||||
|
"G0151",
|
||||||
|
"G0159",
|
||||||
|
"G0163",
|
||||||
|
"G0164",
|
||||||
|
"G0167",
|
||||||
|
"G0178",
|
||||||
|
"G0179",
|
||||||
|
"G0186",
|
||||||
|
"G0187",
|
||||||
|
"G0188"
|
||||||
|
]
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user