{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G6SZVMG522NC5ITZGXZTU2TIHF","short_pith_number":"pith:G6SZVMG5","schema_version":"1.0","canonical_sha256":"37a59ab0ddd69a2ea27935f33a6a6839647b255d82850b7500d57b3fe95f7d3f","source":{"kind":"arxiv","id":"2606.08310","version":1},"attestation_state":"computed","paper":{"title":"To Nuke or Not to Nuke: LLMs' (Missing) Ethical Reasoning and Actions in a High-Stakes Decision-Making Simulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Can Gurkan, H M Abdul Fattah, John Chen, Sihan Cheng","submitted_at":"2026-06-06T19:43:53Z","abstract_excerpt":"Large language models (LLMs) are increasingly deployed as long-horizon agents with decision-making capacities. While LLMs can show ethical competence on dilemmas such as trolley problems, this competence may not translate to complex, agentic scenarios. We study this gap in Civilization V, a multiplayer game with a complex decision-making landscape including economy, diplomacy, technology, and military strategy. Starting from 130 high-tension LLM self-play episodes, in which an LLM player spontaneously escalated nuclear authorization, we replay them across 13 models with three prompt interventi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.08310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-06T19:43:53Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"ebb871b39bd161c0298f42e4b9d9799695f7e34290f2f36a04de4d2f6031f5e3","abstract_canon_sha256":"558dfb3dcc5057fa3bee24df52f73ea44c4c5dd8d6e35dc3dd549d0a7ef4d04d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:33.250739Z","signature_b64":"xHzw8RMqUqc45qXpW9RUNRCPbcOEFfns7JOAUIAWskjfrxThZpGNS3q4pa07kO9Dcq527ZGtuOB9vbD73QwICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37a59ab0ddd69a2ea27935f33a6a6839647b255d82850b7500d57b3fe95f7d3f","last_reissued_at":"2026-06-09T01:05:33.250361Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:33.250361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"To Nuke or Not to Nuke: LLMs' (Missing) Ethical Reasoning and Actions in a High-Stakes Decision-Making Simulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Can Gurkan, H M Abdul Fattah, John Chen, Sihan Cheng","submitted_at":"2026-06-06T19:43:53Z","abstract_excerpt":"Large language models (LLMs) are increasingly deployed as long-horizon agents with decision-making capacities. While LLMs can show ethical competence on dilemmas such as trolley problems, this competence may not translate to complex, agentic scenarios. We study this gap in Civilization V, a multiplayer game with a complex decision-making landscape including economy, diplomacy, technology, and military strategy. Starting from 130 high-tension LLM self-play episodes, in which an LLM player spontaneously escalated nuclear authorization, we replay them across 13 models with three prompt interventi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08310","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.08310/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.08310","created_at":"2026-06-09T01:05:33.250411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08310v1","created_at":"2026-06-09T01:05:33.250411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08310","created_at":"2026-06-09T01:05:33.250411+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6SZVMG522NC","created_at":"2026-06-09T01:05:33.250411+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6SZVMG522NC5ITZ","created_at":"2026-06-09T01:05:33.250411+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6SZVMG5","created_at":"2026-06-09T01:05:33.250411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6SZVMG522NC5ITZGXZTU2TIHF","json":"https://pith.science/pith/G6SZVMG522NC5ITZGXZTU2TIHF.json","graph_json":"https://pith.science/api/pith-number/G6SZVMG522NC5ITZGXZTU2TIHF/graph.json","events_json":"https://pith.science/api/pith-number/G6SZVMG522NC5ITZGXZTU2TIHF/events.json","paper":"https://pith.science/paper/G6SZVMG5"},"agent_actions":{"view_html":"https://pith.science/pith/G6SZVMG522NC5ITZGXZTU2TIHF","download_json":"https://pith.science/pith/G6SZVMG522NC5ITZGXZTU2TIHF.json","view_paper":"https://pith.science/paper/G6SZVMG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08310&json=true","fetch_graph":"https://pith.science/api/pith-number/G6SZVMG522NC5ITZGXZTU2TIHF/graph.json","fetch_events":"https://pith.science/api/pith-number/G6SZVMG522NC5ITZGXZTU2TIHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6SZVMG522NC5ITZGXZTU2TIHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6SZVMG522NC5ITZGXZTU2TIHF/action/storage_attestation","attest_author":"https://pith.science/pith/G6SZVMG522NC5ITZGXZTU2TIHF/action/author_attestation","sign_citation":"https://pith.science/pith/G6SZVMG522NC5ITZGXZTU2TIHF/action/citation_signature","submit_replication":"https://pith.science/pith/G6SZVMG522NC5ITZGXZTU2TIHF/action/replication_record"}},"created_at":"2026-06-09T01:05:33.250411+00:00","updated_at":"2026-06-09T01:05:33.250411+00:00"}