{
  "abstract": "Chemistry language models now predict reactions and retrosynthetic routes with useful accuracy, but they assume that proprietary reaction records can be pooled into a central cluster and that inference runs on abundant accelerators. Neither assumption holds in pharmaceutical and fine-chemical practice, where yield records cannot leave the plant network, the points of use are heterogeneous resource-limited sites, and different laboratories occupy disjoint regions of chemical space. We present ChemFedFusion, a heterogeneity-aware framework for federated chemistry-model training and offloading over collaborative laboratory edge networks. ChemUCP is a chemistry-aware utility–cost predictor that scores a task–node pair by expected chemistry gain, expected latency, and an explicit out-of-distribution risk of emitting unparsable or unreliable chemistry, using a dual-channel tokenizer and a scaffold-coverage encoder that is corrected online from execution feedback. CSAW replaces sample-count aggregation with the product of a scaffold-space complementarity term, a site reliability term, and a weakened volume guard, amplifying rare chemistry while suppressing noisy sites. ARCO couples offloading and aggregation through a shared adaptation matrix and an event-driven asynchronous aggregator with a staleness bound, so that successful offloads teach the aggregator which node is competent for which chemistry task. On Mol-Instruction and USPTO-50K, ChemFedFusion reaches 0.883 Exact and 51.36% Top-1, and on the FedChem suite it reduces regression RMSE by up to 9.99% and classification ROC-AUC improvements are consistent across all nine datasets and three heterogeneity levels. The framework reduces convergence rounds by 22.4% and raises the fraction of answers that are both on time and chemically valid by 8.8 percentage points. A failure analysis shows that the remaining errors are dominated by synthetically infeasible routes that parse correctly, which no validity-based router can detect.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "Andre Williams",
      "orcid": "0009-0000-9889-9808"
    },
    {
      "name": "Shanice Brown"
    },
    {
      "name": "Kevin Thompson"
    },
    {
      "name": "Jamar Campbell"
    },
    {
      "name": "Alicia Morgan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f44f3rppt1jat.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009129/v1",
  "fulltext_url": null,
  "id": "f44f3rppt1jat",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009129/v1",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1702|Privacy-Preserving Technologies in Data"
    ]
  ],
  "openalex": "W7213931134",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009129/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-21",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/f44f3rppt1jat.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:19Z",
      "native_id": "10.26434/chemrxiv.15009129",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009129/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "Collaborative Laboratory Edge Networks",
  "title_text": "Collaborative Laboratory Edge Networks",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/f44f3rppt1jat",
  "venue": "ChemRxiv",
  "versions": []
}