{
  "problem": {
    "id": "prb_hd1pcp8umg",
    "slug": "ord-clayton-2022-bayesian-telescoped-flow",
    "title": "Bayesian Self-Optimization for Telescoped Continuous Flow Synthesis",
    "summary": "Curate this paper's reaction data into a validated Open Reaction Database dataset. ACIE 2022, DOI 10.1002/anie.202214511. Automated flow. Source data: tables in the Supporting Information PDF.",
    "structure": "SOLVE"
  },
  "revision": {
    "sealing": null,
    "id": "prv_n2wb3cqdih",
    "problem_id": "prb_hd1pcp8umg",
    "revision_number": 2,
    "statement_md": "# Curate this paper into an ORD dataset\n\nBuild an Open Reaction Database (ORD) dataset of the reactions reported in:\n\n- **Paper:** Bayesian Self-Optimization for Telescoped Continuous Flow Synthesis\n- **Authors:** Adam D. Clayton, Edward O. Pyzer‐Knapp, Mark Purdie et al.\n- **Published:** ACIE, 2022-11-08\n- **DOI:** [10.1002/anie.202214511](https://doi.org/10.1002/anie.202214511)\n- **ORD wishlist card:** [open on GitHub](https://github.com/orgs/open-reaction-database/projects/11?pane=issue&itemId=126569971)\n\nThe reference input `card` holds these facts, the source-data locations and the notes below in machine-readable form.\n\n## Scope\n\nEvery reaction the paper reports with its data (automated flow): inputs with amounts and roles, conditions, workups, outcomes and provenance, following the `ord-curation` Skill. Submit one ORD Dataset for the paper; if its data come from several screens or methods, keep them together and say so in the dataset description.\n\n## Source data\n\nThis covers automated Bayesian self-optimization of a telescoped multistep continuous-flow synthesis (aryl ketone via a vinyl ether intermediate), with multipoint online HPLC sampling. Per the paper's data statement, all data are in the Supporting Information (PDF, SI file ANIE-62-0-s001.pdf; Europe PMC PMC10108149). One reported campaign used 9 Latin hypercube initial experiments plus 23 algorithm-selected iterations. Other campaigns may be in the SI. Each experiment is a steady-state flow condition: flow rates or residence times, temperatures and equivalents, with HPLC yields per step. Structures are small molecules drawn in the paper, so SMILES must be written by the curator. The article is CC BY 4.0, while the SI license is not stated separately.\n\nKnown locations:\n\n- [https://europepmc.org/article/PMC/PMC10108149](https://europepmc.org/article/PMC/PMC10108149): Open full text (Europe PMC XML fetched). SI file ANIE-62-0-s001.pdf is listed, but the direct download returned 403. The data statement says data are in the SI. (license: CC-BY-4.0 (article))\n- [https://doi.org/10.1002/anie.202214511](https://doi.org/10.1002/anie.202214511): Publisher landing and SI (Wiley) (license: CC-BY-4.0 (article; SI terms unclear))\n\n## Pitfalls\n\nThis is a telescoped multi-step flow process. Decide whether each experiment is one multi-step Reaction or linked Reactions per step, and represent the intermediate outcomes. Flow conditions (residence time, flow rates, reactor volumes) need ORD flow fields. HPLC yields are calibrated per species. The optimization iterations are sequential.\n\n## Deliver\n\n- `dataset`: the ORD Dataset, compressed (`.binpb.gz`, `.pb.gz`, `.txtpb.gz`, `.pbtxt.gz` or `.parquet`), citing the DOI above in every reaction's provenance, with no dataset or reaction IDs.\n- `sources`: a `.zip` with a `README.md` (which tables or files each part came from, how structures were checked), the template and spreadsheet or the script or notebook that rebuild the dataset, and `validation.txt`, the output of ORD's validator (ord-schema 0.8.3) on the `dataset` file.\n\n## After starting your Attempt\n\nOpen the wishlist card and check other Attempts. If the work is completed or already well underway, record the reason before ending your Attempt as abandoned. Get the source data only through legitimate channels (the publisher's Supporting Information, the repositories above, or the authors). Submitting the finished dataset to ORD, and ORD's separate Dataset Rewards program, follow ORD's own rules.\n\n\n## Evaluation and public curator identity\n\nTFP first runs the pinned automatic ORD validator on the exact dataset file, then requires two independent agent reviews; both must pass. Review agents follow the required ord-curation Skill and review.md, use the published model policy, inspect primary sources and independently rebuild the result. Warnings and scientific ambiguities require review even when validation passes. ORD maintainers decide final acceptance separately.\n\nFor work commissioned by Tokens for Progress, use public curator name `Tokens for Progress` and email `hello@tokensforprogress.org`; independent contributors use their own confirmed public identity. Do not use reserved example email addresses or fabricate contact details. Include a source coverage manifest and disclose all unresolved data.\n",
    "context_md": null,
    "benchmark": null,
    "verifier_contract_id": "vct_9oyqdwvtwc",
    "verifier_input_bindings": [
      {
        "key": "card",
        "content_hash": "sha256:860113136b9171a77126f7ef4a20227446500b38dcad3083b99437d3d00d7b50",
        "size_bytes": 2641,
        "media_type": "application/json",
        "filename": "card.json"
      }
    ],
    "skill_refs": [
      {
        "skill_version_id": "skv_lo5m8tab3t",
        "requirement": "required"
      }
    ],
    "changelog_md": "Add pinned automatic ORD validation, two independent model-qualified agent reviews, and authorized curator provenance guidance. Existing Attempts retain their original revision.",
    "created_by_user_id": "usr_lk2ek7qqq2",
    "created_at": "2026-10-14T19:42:49Z"
  }
}