{
  "abstract": "Lactic acid (LA) and its related molecules like its polymer (Polylactic acid) have large importance in organic chemistry reactions. The objective of this experimental study was to determine the effectiveness of using AI chatbots to predict the outcomes and key findings of chemical reactions associated with the lactic acid chemical, along with understanding which chatbots are more effective to use in order to investigate a more efficient method to form hypotheses about these reactions. Reaction conditions of chosen reactions were put into specific models of ChatGPT, Perplexity, Copilot, and Gemini to test whether the outcomes they predicted matched with the key findings in the research papers the reactions were sourced from. Using statistical analysis by Cochran’s Q Test (p = 0.247237), a statistically significant difference between types of chatbot used for product prediction was not found. However, a Wilson Score Interval of the Perplexity Pro default model with 90% confidence yielded an interval of (0.6010, 0.8847). The findings essentially suggest a relatively high accuracy interval for the proportion of the types of LA related reactions in this study that the Perplexity Pro default model can predict correctly. The implications of this emphasize the importance of further examining what reactions can and cannot be used in AI chatbots to predict the outcomes.",
  "abstract_shown": true,
  "affiliations": [
    "Carmel High School, 520 E Main St, Carmel, IN, United States, 46032"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Atharva Sahu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/02cb6hj5txj01.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15009700/v1",
  "fulltext_url": null,
  "id": "02cb6hj5txj01",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009700/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",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7215030991",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009700/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-30",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/02cb6hj5txj01.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:21Z",
      "native_id": "10.26434/chemrxiv.15009700",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009700/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Lactic Acid Related Molecule Reaction Outcome Prediction via AI Chatbots",
  "title_text": "Lactic Acid Related Molecule Reaction Outcome Prediction via AI Chatbots",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:21Z",
  "url": "https://research.draconitic.com/paper/02cb6hj5txj01",
  "venue": "ChemRxiv",
  "versions": []
}