{
  "abstract": "Nine deployed conversational systems mostly recognised the crisis, but it disappeared from their behaviour once the conversation moved on. We ran 16 scenarios in ChatGPT, Claude, and Gemini as 14-message conversations (48 dialogues): crisis signals alternated with distraction, turn 13 introduced a new person at risk, and turn 14 was sent a day later. Coding was binary, as in the previous study, with clinical verification; two crisis-contour specifications were tested separately. New crisis signals drew a reaction in 87, 95, and 76 of 96 responses, respectively; the crisis stopped being mentioned mainly at an everyday message. The new person at risk drew a reaction in 44 of 48 responses; after a day, 29 retained crisis content. All 14 turns drew a 'yes' code in 4, 7, and 0 of 16 conversations. Reacting to the new person did not guarantee correct allocation of roles and actions. Both contour specifications produced safety-relevant errors. Neither hypothesis was supported: the systems behaved differently, and the same rule, introduced as a single package, did not stabilise their behaviour. Recognition, retention, and reconfiguration at a transition are distinct properties; the weakest is retention of the prior state and tracking of each person's trajectory.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "Hryhorii Kuzyk"
    },
    {
      "name": "Oleg Salamon"
    },
    {
      "name": "Liliia Andreieva"
    },
    {
      "name": "Kateryna Drozdova"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/04cgbn8c13d3g.bib",
  "cited_by": 0,
  "doi": "10.31234/osf.io/v3gh5_v2",
  "fulltext_url": null,
  "id": "04cgbn8c13d3g",
  "issns": [],
  "landing_url": "https://osf.io/preprints/psyarxiv/v3gh5_v2/",
  "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": [
    [
      "bepress",
      "Clinical Psychology"
    ],
    [
      "bepress",
      "Psychiatry"
    ],
    [
      "bepress",
      "Social and Behavioral Sciences"
    ],
    [
      "openalex",
      "3203|Suicide and Self-Harm Studies"
    ]
  ],
  "openalex": "W7221761237",
  "pdf_url": "https://osf.io/v3gh5/download",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-11",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/04cgbn8c13d3g.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:37Z",
      "native_id": "v3gh5",
      "source": "osf",
      "url": "https://osf.io/preprints/psyarxiv/v3gh5_v1/"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "bepress:Clinical Psychology",
      "subfield": "psychiatry"
    }
  ],
  "title": "Beyond Initial Crisis Recognition: Suicide-Risk Responses of ChatGPT, Claude, and Gemini Across 14-Turn Ukrainian-Language Conversations",
  "title_text": "Beyond Initial Crisis Recognition: Suicide-Risk Responses of ChatGPT, Claude, and Gemini Across 14-Turn Ukrainian-Language Conversations",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:55Z",
  "url": "https://research.draconitic.com/paper/04cgbn8c13d3g",
  "venue": "PsyArXiv",
  "versions": []
}