tao-generate-referring-expressions

CID baeareiasusvjdj4zcaout6x4ocsifajlpq54ooiqcd3sofyfyervdhdkm4
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 baeareiblixor4etjdhakyy6qt45glewyzkneq5bc76cvhxkkssbrp5brgm: empty referrer baeareiblixor4etjdhakyy6qt45glewyzkneq5bc76cvhxkkssbrp5brgm
OASF record valid
Yes

Record

Authors
NVIDIA
Created
2026-09-14T00:59:19Z
Pulled
20 hours ago
Modules
core/language_model/agentskills
Raw OASF record (JSON)
{
  "authors": [
    "NVIDIA"
  ],
  "created_at": "2026-09-14T00:59:19Z",
  "description": "Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distillation. Use when the user wants to generate referring-expression annotations from images with KITTI labels, build region descriptions, produce grouped grounding phrases tied to bboxes, run a double-check verification pass on grounding expressions, auto-label traffic / scene images for referring datasets, or run the image_referring_expression pipeline. Triggers include 'referring expression', 'region description', 'KITTI labels', 'spatial relationship annotation', 'auto-label image referring expression', 'image_referring_expression'.",
  "domains": [
    {
      "id": 402,
      "name": "trust_and_safety/content_moderation"
    },
    {
      "id": 205,
      "name": "finance_and_business/retail"
    }
  ],
  "modules": [
    {
      "artifact": {
        "data": "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",
        "digest": "sha256:9c1f52ebcacb715540c03a661c1b6ee6e5cc185c1899bf8130d3f57d1409cfa7",
        "media_type": "application/agent-skills+gzip",
        "size": 18171
      },
      "data": {
        "artifacts": [
          {
            "artifact_hash": "sha256:b370bd3c0e20804b143257248aa88948a1df91f4cc9802e442d455dc37cb7504",
            "path": "BENCHMARK.md",
            "type": "other"
          },
          {
            "artifact_hash": "sha256:45fe82108e99607ff138b73bd5b3272e8b8e10e7e5fd35d3f00e5a9afa493c78",
            "path": "evals/evals.json",
            "type": "other"
          },
          {
            "artifact_hash": "sha256:b73ad4e46ba38a0be0a2175f489cf3376d37f8f868928dc6b9fc0907956365e0",
            "path": "references/configuration.md",
            "type": "reference"
          },
          {
            "artifact_hash": "sha256:57ec5979e46e75a4b17845fabb9420d1ae4ea4f73690547fecba3831a2611611",
            "path": "references/skill_info.yaml",
            "type": "reference"
          },
          {
            "artifact_hash": "sha256:da96d9f56ba2a038c3eab3b160e933fd7756b55baf8dbb9431b6d50055eef300",
            "path": "references/vllm_server.md",
            "type": "reference"
          },
          {
            "artifact_hash": "sha256:6f37c79e32a62a899223a90bf9ec85e2807f5440a14fefd2ba11b468ccb1fbb4",
            "path": "skill-card.md",
            "type": "other"
          },
          {
            "artifact_hash": "sha256:d7a836db82edebfb0b1382cd91e4e97b8054897e506bedf8982c57565bbc95ab",
            "path": "skill.oms.sig",
            "type": "other"
          }
        ],
        "skill_file": "SKILL.md",
        "skill_manifest": {
          "allowed_tools": [
            "Read",
            "Bash",
            "Write"
          ],
          "compatibility": [
            "Requires docker + nvidia-container-toolkit + at least one VLM endpoint (Gemini API key or OpenAI-compatible)."
          ],
          "description": "Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distillation. Use when the user wants to generate referring-expression annotations from images with KITTI labels, build region descriptions, produce grouped grounding phrases tied to bboxes, run a double-check verification pass on grounding expressions, auto-label traffic / scene images for referring datasets, or run the image_referring_expression pipeline. Triggers include 'referring expression', 'region description', 'KITTI labels', 'spatial relationship annotation', 'auto-label image referring expression', 'image_referring_expression'.",
          "frontmatter_metadata": {
            "author": "NVIDIA Corporation",
            "version": "0.1.0"
          },
          "license": "Apache-2.0",
          "name": "tao-generate-referring-expressions",
          "version": "0.1.0"
        }
      },
      "id": 10302,
      "name": "core/language_model/agentskills"
    }
  ],
  "name": "tao-generate-referring-expressions",
  "schema_version": "1.1.0",
  "skills": [
    {
      "id": 20301,
      "name": "computer_vision/image_editing/instructed_image_editing"
    },
    {
      "id": 103,
      "name": "language_processing/language_generation"
    }
  ],
  "version": "0.1.0"
}

Advertisements

GossipSub broadcast

First seen
1 month ago
Last seen
27 minutes ago
Announcements
1,156
Publishers
1
Topics
dir/labels/v1
Every 2 hours, last 3 days
Announcements Publishers
Announcements 30
Nov 14 Nov 15 Nov 16
10 Publishers

DHT add-provider

DHT key
QmPbRgP5m85s6k94jWNae9RdiafhPXz9NoaT1pWAbVRoQz
First seen
6 days, 23 hours ago
Last seen
27 minutes ago
Requests
155
Providers
1
Lookups
6
Seekers
6
Last lookup
20 hours ago
Every 2 hours, last 3 days
ADD_PROVIDER GET_PROVIDERS Providers
Requests 30
Nov 14 Nov 15 Nov 16
10 Providers

Skills

  • computer_vision 1
    • image_editing 1
      • instructed_image_editing
  • language_processing 1
    • language_generation

Domains

  • finance_and_business 1
    • retail
  • trust_and_safety 1
    • content_moderation

Locators

None

Annotations

version
0.1.0
oasf-version
1.1.0
name
tao-generate-referring-expressions

GossipSub publishers

DHT providers

github.com/libp2p/go-libp2p Expires in 1 day, 23 hours
Requests
155
First seen
6 days, 23 hours ago
Last seen
27 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
20 hours ago 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu 1 3,459 ms 0 ms 9,957 ms 13,417 ms 0 OK
1 day, 22 hours ago 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu 1 10,000 ms 0 ms 4,849 ms 14,850 ms 0 OK
3 days ago 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu 1 7,723 ms 0 ms 12,676 ms 20,400 ms 0 OK
4 days, 2 hours ago 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu 1 9,941 ms 0 ms 6,161 ms 16,103 ms 0 OK
5 days, 4 hours ago 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu 1 6,410 ms 0 ms 12,259 ms 18,669 ms 0 OK
6 days, 6 hours ago 12D3KooWLf9p3cedc86xGQBaqak6rAFmQk1HxKAK1yh7umHE3amu 1 4,812 ms 0 ms 7,598 ms 12,410 ms 1 OK