- Announcements
- 1,155
- Messages
- 1,155
- Relayers
- 1
- Avg. size
- 474 B
- First seen
- 1 month ago
- Last seen
- 22 minutes ago
- Topics
- dir/labels/v1
AGNTCY monitoring is a work in progress. Send your feedback to
[email protected].
tao-train-mask-auto-label
CID
baeareigbt43rvtu4r5pdwfqcgtfacy7w3zyknqw5pyyvhledrsbtiuhajy
v0.1.0
OASF 1.1.0
Not signed
Security
- CID matches content
- Yes
- Signed
- No
- 0 signature(s)
- Trusted (signature verified)
- No
- pull signatures: pull referrer baeareibu4l7y2amy5yf65xkmnluop6aherxptzuqiharkfa2nfuowcr5bq: empty referrer baeareibu4l7y2amy5yf65xkmnluop6aherxptzuqiharkfa2nfuowcr5bq
- OASF record valid
- Yes
Record
- Authors
- NVIDIA
- Created
- 2026-09-14T00:59:45Z
- Pulled
- 43 minutes ago
- Modules
- core/language_model/agentskills
Raw OASF record (JSON)
{
"authors": [
"NVIDIA"
],
"created_at": "2026-09-14T00:59:45Z",
"description": "MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-MAE backbone. Use when training, evaluating, or running inference for a TAO MAL model. Trigger phrases include \"train MAL\", \"Mask Auto-Label\", \"weakly-supervised segmentation\", \"box-prompted segmentation\", \"minimal-annotation mask prediction\".",
"domains": [
{
"id": 205,
"name": "finance_and_business/retail"
},
{
"id": 402,
"name": "trust_and_safety/content_moderation"
},
{
"id": 2005,
"name": "retail_and_ecommerce/point_of_sale"
}
],
"modules": [
{
"artifact": {
"data": "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",
"digest": "sha256:988d3d156c69bcaf2162471bda8dea846dcf406a3ff61be4f9eca76867ddf895",
"media_type": "application/agent-skills+gzip",
"size": 18162
},
"data": {
"artifacts": [
{
"artifact_hash": "sha256:46ba0ce5ac24f813fc6d14b822f5b00f9f90bab754c6be4d27b18e7acea79779",
"path": "BENCHMARK.md",
"type": "other"
},
{
"artifact_hash": "sha256:442b070811e8efeec69342d0103cd0322a253727fed0cf5525de5345b773aa1a",
"path": "evals/evals.json",
"type": "other"
},
{
"artifact_hash": "sha256:5c52d916a7fdbc042e2cabb3c40d78e5259b337a965c14359de688a20c1b385b",
"path": "references/skill_info.yaml",
"type": "reference"
},
{
"artifact_hash": "sha256:dfcd1022ba2b87dc8d6c5b054b0e3da0682f4680d59250421bdfd6c2db1a1f94",
"path": "references/spec_template_evaluate.yaml",
"type": "reference"
},
{
"artifact_hash": "sha256:0f84115c3bddc2acbda6e3b8edbe0c39f7ad1c225ca862e71f2436b96d7dcf04",
"path": "references/spec_template_inference.yaml",
"type": "reference"
},
{
"artifact_hash": "sha256:c5e0bb5d56f00f8abf7ad5e17b3ef7d940c1554cc5c5ec6a3d14b134e2031d3c",
"path": "references/spec_template_train.yaml",
"type": "reference"
},
{
"artifact_hash": "sha256:46185b04e5e71446c364e80d2ed9c8277ba1235dbfbe3856b24c6997bb272cb9",
"path": "schemas/evaluate.schema.json",
"type": "other"
},
{
"artifact_hash": "sha256:6c09077c6addc2f663297c4b66eef2ae1455b5339773a25c9149d8563765d46d",
"path": "schemas/inference.schema.json",
"type": "other"
},
{
"artifact_hash": "sha256:a9e80216c3a497427940509f14f032021385a2cce035a7753768f0534d6c86fb",
"path": "schemas/manifest.json",
"type": "other"
},
{
"artifact_hash": "sha256:5a4e928c1d836b7c33692e01d5cfb1f1742d7a8c3d0a920dc82e4cfe6654fe37",
"path": "schemas/train.schema.json",
"type": "other"
},
{
"artifact_hash": "sha256:99f12160998aadc04ebf71d6de2228ff3e2daa715459d67da68561743e255c78",
"path": "skill-card.md",
"type": "other"
},
{
"artifact_hash": "sha256:4104e68343dca32269cf5e53e8717a08bc18fe0060831a16db686811edb450f6",
"path": "skill.oms.sig",
"type": "other"
}
],
"skill_file": "SKILL.md",
"skill_manifest": {
"allowed_tools": [
"Read",
"Bash"
],
"compatibility": [
"Requires docker + nvidia-container-toolkit."
],
"description": "MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-MAE backbone. Use when training, evaluating, or running inference for a TAO MAL model. Trigger phrases include \"train MAL\", \"Mask Auto-Label\", \"weakly-supervised segmentation\", \"box-prompted segmentation\", \"minimal-annotation mask prediction\".",
"frontmatter_metadata": {
"author": "NVIDIA Corporation",
"version": "0.1.0"
},
"license": "Apache-2.0",
"name": "tao-train-mask-auto-label",
"version": "0.1.0"
}
},
"id": 10302,
"name": "core/language_model/agentskills"
}
],
"name": "tao-train-mask-auto-label",
"schema_version": "1.1.0",
"skills": [
{
"id": 20104,
"name": "computer_vision/image_analysis/mask_generation"
},
{
"id": 70101,
"name": "ai_ml_engineering/classical_ml/supervised_model_training"
},
{
"id": 103,
"name": "language_processing/language_generation"
}
],
"version": "0.1.0"
}
Advertisements
GossipSub broadcast
- First seen
- 1 month ago
- Last seen
- 22 minutes ago
- Announcements
- 1,155
- Publishers
- 1
- Topics
- dir/labels/v1
Announcements
30
Nov 14
Nov 15
Nov 16
10
Publishers
DHT add-provider
- DHT key
-
QmbNUCuBJ1BJueuzw4Uc5bZ9KYVv9S9BRCj5exMus8s4e1
- First seen
- 6 days, 23 hours ago
- Last seen
- 22 minutes ago
- Requests
- 154
- Providers
- 1
- Lookups
- 7
- Seekers
- 7
- Last lookup
- 43 minutes ago
Requests
30
Nov 14
Nov 15
Nov 16
10
Providers
Skills
-
ai_ml_engineering 1
-
classical_ml 1
- supervised_model_training
-
-
computer_vision 1
-
image_analysis 1
- mask_generation
-
-
language_processing 1
- language_generation
Domains
-
finance_and_business 1
- retail
-
retail_and_ecommerce 1
- point_of_sale
-
trust_and_safety 1
- content_moderation
Locators
None
Annotations
- name
- tao-train-mask-auto-label
- version
- 0.1.0
- oasf-version
- 1.1.0
GossipSub publishers
DHT providers
- Requests
- 154
- First seen
- 6 days, 23 hours ago
- Last seen
- 22 minutes ago
- Connection address
- /ip4/3.140.179.223/udp/57133/quic-v1
Listen addresses (3)
- /ip4/10.0.17.42/tcp/5555
- /ip4/127.0.0.1/tcp/5555
- /ip4/3.150.168.105/tcp/5555
Protocols (14)
- /dir/rpc/1.0.0
- /floodsub/1.0.0
- /ipfs/id/1.0.0
- /ipfs/id/push/1.0.0
- /ipfs/ping/1.0.0
- /libp2p/autonat/1.0.0
- /libp2p/circuit/relay/0.2.0/hop
- /libp2p/circuit/relay/0.2.0/stop
- /libp2p/dcutr
- /meshsub/1.0.0
- /meshsub/1.1.0
- /meshsub/1.2.0
- /meshsub/1.3.0
- dir/kad/1.0.0
Latest pull attempts
| Time | Provider | Providers found | Lookup | Connect | Pull | Total | CID | Signatures | Trusted | OASF | Result |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 43 minutes ago | 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu | 1 | 10,001 ms | 0 ms | 7,970 ms | 17,972 ms | 0 | OK | |||
| 1 day, 3 hours ago | 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu | 1 | 5,700 ms | 0 ms | 12,339 ms | 18,040 ms | 0 | OK | |||
| 2 days, 4 hours ago | 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu | 1 | 6,623 ms | 0 ms | 11,341 ms | 17,964 ms | 0 | OK | |||
| 3 days, 7 hours ago | 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu | 1 | 7,732 ms | 0 ms | 9,705 ms | 17,438 ms | 0 | OK | |||
| 4 days, 9 hours ago | 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu | 1 | 6,622 ms | 0 ms | 12,680 ms | 19,303 ms | 0 | OK | |||
| 5 days, 10 hours ago | 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu | 1 | 5,828 ms | 0 ms | 10,352 ms | 16,180 ms | 0 | OK | |||
| 6 days, 13 hours ago | 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu | 1 | 7,034 ms | 0 ms | 6,500 ms | 13,535 ms | 1 | OK |