{
 "id": "zetomatoz/guidellm-agentic-coding-trajectories",
 "owner": "zetomatoz",
 "name": "guidellm-agentic-coding-trajectories",
 "downloads": 98,
 "likes": 5,
 "last_modified": "2026-09-29T23:10:42.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "derivative-multi-source",
 "licence_link": "LICENSE",
 "file_licence": "cc-by-4.0",
 "licence_files": [
  "LICENSE"
 ],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "This is an adapted, sampled benchmark derived from [Thoughtworks/agentic-coding-trajectories](https://huggingface.co/datasets/thoughtworks/agentic-coding-trajectories) (revision `cef72d1f4d0caabf85937adf8337a14b7522c782`), itself a derivative of three upstream trajectory datasets. Changes here: sample and deduplicate sessions, count output targets with a Qwen tokenizer, and select the original sample using an estimated context budget. This revision recovers native tool-call metadata and recorded results for the sampled sessions, packs conversations into GuideLLM graphs, substitutes one mock function for native tools, and moves the existing fixed output targets to text continuations. Text-command sources retain their original flattened prompts. Context estimates are recalculated for the expanded workload. These files include original trajectory text. Credit Thoughtworks and the upstream dataset creators when reusing or sharing them.\n\n`license: other` and `license_name: derivative-multi-source` describe the mixed provenance; they do **not** grant a single new license for all rows. See [LICENSE](LICENSE) for source links and terms. Every row includes `source_dataset` and `source_id` so its upstream source can be identified. The 8, 24, and 48 turn configurations contain 90, 450, and 90 rows respectively; source records can occur in more than one configuration.\n\n| `source_dataset` | Upstream trajectories | Published dataset license | Rows in 8 / 24 / 48 turn configs |\n| --- | --- ",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "94fe7ff81d801109103b1ccee32207b10257c247",
 "stated_evidence": "https://huggingface.co/datasets/zetomatoz/guidellm-agentic-coding-trajectories/blob/94fe7ff81d801109103b1ccee32207b10257c247/README.md",
 "file_evidence": "https://huggingface.co/datasets/zetomatoz/guidellm-agentic-coding-trajectories/blob/94fe7ff81d801109103b1ccee32207b10257c247/LICENSE",
 "card_nc": false
}