# Attribution

Loom Tapestry 3 was trained from scratch (random-init lineage — grown from Textile Labs'
own Loom Weave 3, no third-party checkpoint). Grounded-reading rows embed real encyclopedic
prose. Training data, all permissively licensed:

| slice | source | licence |
|---|---|---|
| grounded reading | SQuAD 2.0 | CC BY-SA 4.0 |
| multi-hop grounded reading | HotpotQA | CC BY-SA 4.0 |
| when to reach for a tool | MASSIVE / CLINC150 | CC BY 4.0 / CC BY 3.0 |
| instruction following | databricks-dolly-15k | CC BY-SA 3.0 |
| multi-turn dialogue | OpenAssistant OASST1 | Apache 2.0 |
| tokenizer coverage of real prose | HuggingFaceFW/fineweb-edu | ODC-By 1.0 |
| encyclopedic passages | Wikipedia | CC BY-SA |
| identity, limits, warmth, attribution | Textile Labs | — |

No language model wrote any training query. No real user data was used. Model weights: MIT.