{
  "abstract": "We introduce SNACK, a string representation for probabilistic graph generation that enables language models to generate graphs with discrete node and edge features. SNACK linearizes graphs by encoding the nonzero entries of the lower-triangular adjacency matrix, establishing a bijective correspondence between valid sequences and ordered adjacency matrices. This design enables invalid logit masking to enforce structural constraints, such as chemical valence and ordering rules, thereby guaranteeing 100% valid generated sequences while sticking to standard language modeling for effective training. SNACK also enables principled string-based GFlowNet training by explicitly accounting for node-ordering symmetries. Across standard graph-generation tasks and molecular distribution-learning benchmarks, SNACK achieves competitive sample quality, while substantially improving the throughput of GFlowNet training relative to graph-based generation. Probing analyses further show that models trained on SNACK encode meaningful local and global graph structure despite receiving only sequential supervision. These results position SNACK as a practical framework for probabilistic graph generation with deep sequence models.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.19781",
  "author_total": 4,
  "authors": [
    {
      "name": "Hohyun Kim"
    },
    {
      "name": "Hyesung Kim"
    },
    {
      "name": "Min-hwan Oh"
    },
    {
      "name": "Seunggeun Lee"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/b2dk04zzywqg5.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.19781",
  "fulltext_url": null,
  "id": "b2dk04zzywqg5",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.19781",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1707|Graph Theory and Algorithms"
    ]
  ],
  "openalex": "W7222272721",
  "pdf_url": "https://arxiv.org/pdf/2610.19781",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/b2dk04zzywqg5.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:49Z",
      "native_id": "2610.19781",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.19781"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "SNACK: A Sequential Notation Framework for Probabilistic Graph Generation",
  "title_text": "SNACK: A Sequential Notation Framework for Probabilistic Graph Generation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:49Z",
  "url": "https://research.draconitic.com/paper/b2dk04zzywqg5",
  "venue": "arXiv",
  "versions": []
}