{
  "abstract": "Artificial intelligence today is mainly trained on transformer architecture and later fine-tuned along\n\nwith data segregation requiring enormous training data and machine intensive processes . Unlike a\n\ntraditional transformer, the research of Herebot started with a simple question: How do cognitive\n\nbeings actually learn some concepts in scoped or classified context? And can that same mecha-\n\nnism be applied in order to learn within machine learning concepts rather than using a transformer\n\nconcept? The main difference where the transformer and Herebot differ is, transformer does encod-\n\ning and embedding, tokenization etc. processes which includes heavy computational processing.\n\nWhereas an alternative architecture can hardcode documented learning traits of cognitive beings\n\nand use them instead of transformer-like training to make or justify the learning process. The\n\nresearch due to its complexity currently is focused on textual data and theories on cognition and\n\nmemory. As biologically and psychologically the cognitive being’s mind and its working isn’t\n\nfully documented yet, but even though a major portion is theoretics (theory papers as cited) exists,\n\ncomputer algorithms from these were derived for Herebot.",
  "abstract_shown": true,
  "affiliations": [
    "none"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Hrirake Hrishi Singh",
      "orcid": "0009-0004-9511-3389"
    },
    {
      "name": "Shukla Shubhra",
      "orcid": "0009-0009-2293-9311"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7jcbgdhtxy32b.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23459018",
  "fulltext_url": null,
  "id": "7jcbgdhtxy32b",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23459018",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23459018/files/paper.pdf.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-18",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7jcbgdhtxy32b.ris",
  "sources": [
    {
      "first_seen": "2026-11-01T12:20:55Z",
      "native_id": "23459018",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23459018"
    }
  ],
  "subjects": [],
  "title": "HereBot: An Artificial Curiosity Engine for One-Shot Language Learning in a Non-Transformer Cognitive Architecture",
  "title_text": "HereBot: An Artificial Curiosity Engine for One-Shot Language Learning in a Non-Transformer Cognitive Architecture",
  "type": "preprint",
  "updated_at": "2026-11-01T12:20:55Z",
  "url": "https://research.draconitic.com/paper/7jcbgdhtxy32b",
  "venue": "Zenodo",
  "versions": []
}