Files
html/data/v71_action_plan.json.GOLD-19avr-pre-v67-items
opus 00107fd6fa
Some checks failed
WEVAL NonReg / nonreg (push) Has been cancelled
auto-sync-1945
2026-04-19 19:45:01 +02:00

148 lines
5.1 KiB
Plaintext

{
"updated_at": "2026-04-18T00:58:22+00:00",
"items": [
{
"id": "act_seed_1",
"title": "Wire RAGAS evaluator to sovereign API",
"source": "github-clone",
"github_url": "https:\/\/github.com\/explodinggradients\/ragas",
"priority": "critical",
"category": "hallucination",
"status": "backlog",
"created_at": "2026-04-18T00:03:32+00:00",
"eta": "V71"
},
{
"id": "act_seed_2",
"title": "Clone HELM + integrate 6 benchmarks",
"source": "github-clone",
"github_url": "https:\/\/github.com\/stanford-crfm\/helm",
"priority": "critical",
"category": "benchmark",
"status": "backlog",
"created_at": "2026-04-18T00:03:32+00:00",
"eta": "V72"
},
{
"id": "act_seed_3",
"title": "HaluEval 35k samples wiring",
"source": "github-clone",
"github_url": "https:\/\/github.com\/RUCAIBox\/HaluEval",
"priority": "high",
"category": "hallucination",
"status": "backlog",
"created_at": "2026-04-18T00:03:32+00:00",
"eta": "V72"
},
{
"id": "act_seed_4",
"title": "FActScore atomic facts pipeline",
"source": "github-clone",
"github_url": "https:\/\/github.com\/shmsw25\/FActScore",
"priority": "high",
"category": "factuality",
"status": "backlog",
"created_at": "2026-04-18T00:03:32+00:00",
"eta": "V72"
},
{
"id": "act_seed_5",
"title": "HarmBench red-team tests",
"source": "github-clone",
"github_url": "https:\/\/github.com\/centerforaisafety\/HarmBench",
"priority": "high",
"category": "safety",
"status": "backlog",
"created_at": "2026-04-18T00:03:32+00:00",
"eta": "V72"
},
{
"id": "act_seed_6",
"title": "Embed model sentence-transformers",
"source": "github-clone",
"github_url": "https:\/\/github.com\/UKPLab\/sentence-transformers",
"priority": "critical",
"category": "rag",
"status": "backlog",
"created_at": "2026-04-18T00:03:32+00:00",
"eta": "V71"
},
{
"id": "act_seed_7",
"title": "Wire Langfuse to SSE orchestrator",
"source": "source-pure",
"github_url": "",
"priority": "medium",
"category": "monitoring",
"status": "in_progress",
"created_at": "2026-04-18T00:03:32+00:00",
"eta": "V72"
},
{
"id": "act_seed_8",
"title": "Gunicorn 4 workers sovereign",
"source": "source-pure",
"github_url": "",
"priority": "medium",
"category": "infra",
"status": "backlog",
"created_at": "2026-04-18T00:03:32+00:00",
"eta": "V71"
},
{
"id": "act_seed_9",
"title": "TruthfulQA benchmark run",
"source": "github-clone",
"github_url": "https:\/\/github.com\/sylinrl\/TruthfulQA",
"priority": "medium",
"category": "hallucination",
"status": "backlog",
"created_at": "2026-04-18T00:03:32+00:00",
"eta": "V72"
},
{
"id": "act_seed_10",
"title": "Training weval-brain-v5 DPO alignment",
"source": "training",
"github_url": "",
"priority": "medium",
"category": "finetuning",
"status": "backlog",
"created_at": "2026-04-18T00:03:32+00:00",
"eta": "V73"
},
{
"id": "act_69e2d175af469",
"title": "action wire ragas evaluator",
"source": "github-clone",
"github_url": "",
"priority": "critical",
"category": "rag",
"status": "backlog",
"created_at": "2026-04-18T00:33:57+00:00",
"eta": "V72"
},
{
"id": "act_69e2d70ec8cd3",
"title": "action wire ragas",
"source": "github-clone",
"github_url": "https:\/\/github.com\/explodinggradients\/ragas",
"priority": "critical",
"category": "hallucination",
"status": "backlog",
"created_at": "2026-04-18T00:57:50+00:00",
"eta": "V72"
},
{
"id": "act_69e2d72e4aa69",
"title": "plan add wire ragas priority critical eta V72 github https:\/\/github.com\/explodin",
"source": "github-clone",
"github_url": "https:\/\/github.com\/explodinggradients\/ragas",
"priority": "critical",
"category": "rag",
"status": "backlog",
"created_at": "2026-04-18T00:58:22+00:00",
"eta": "V72"
}
]
}