{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FJYPH4DBXJXN5QVS7BTPAZCC7Q","short_pith_number":"pith:FJYPH4DB","schema_version":"1.0","canonical_sha256":"2a70f3f061ba6edec2b2f866f06442fc34e7c2110c113c673f66731aba6e00f3","source":{"kind":"arxiv","id":"2504.20980","version":1},"attestation_state":"computed","paper":{"title":"Jekyll-and-Hyde Tipping Point in an AI's Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","nlin.AO","physics.comp-ph","physics.soc-ph"],"primary_cat":"cs.AI","authors_text":"Frank Yingjie Huo, Neil F. Johnson","submitted_at":"2025-04-29T17:50:29Z","abstract_excerpt":"Trust in AI is undermined by the fact that there is no science that predicts -- or that can explain to the public -- when an LLM's output (e.g. ChatGPT) is likely to tip mid-response to become wrong, misleading, irrelevant or dangerous. With deaths and trauma already being blamed on LLMs, this uncertainty is even pushing people to treat their 'pet' LLM more politely to 'dissuade' it (or its future Artificial General Intelligence offspring) from suddenly turning on them. Here we address this acute need by deriving from first principles an exact formula for when a Jekyll-and-Hyde tipping point o"},"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":"2504.20980","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-29T17:50:29Z","cross_cats_sorted":["cs.CY","nlin.AO","physics.comp-ph","physics.soc-ph"],"title_canon_sha256":"b3c6af1bca708618c1b60b197f854828648e1c90a1f78d0552a798d7bd65c820","abstract_canon_sha256":"4a783b0134b7a04a9025046e039c954971fb4b41d4ef8fe2def15c5515c487bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:52.388340Z","signature_b64":"eBU+G3Vhj3MxJeffV42pAcVpiVkk346+dXcG7uTUFxuENSd8eG8V5SO6qehoNiGCVRq/aqnk7ae+qrdxCtgMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a70f3f061ba6edec2b2f866f06442fc34e7c2110c113c673f66731aba6e00f3","last_reissued_at":"2026-07-05T10:55:52.387864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:52.387864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Jekyll-and-Hyde Tipping Point in an AI's Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","nlin.AO","physics.comp-ph","physics.soc-ph"],"primary_cat":"cs.AI","authors_text":"Frank Yingjie Huo, Neil F. Johnson","submitted_at":"2025-04-29T17:50:29Z","abstract_excerpt":"Trust in AI is undermined by the fact that there is no science that predicts -- or that can explain to the public -- when an LLM's output (e.g. ChatGPT) is likely to tip mid-response to become wrong, misleading, irrelevant or dangerous. With deaths and trauma already being blamed on LLMs, this uncertainty is even pushing people to treat their 'pet' LLM more politely to 'dissuade' it (or its future Artificial General Intelligence offspring) from suddenly turning on them. Here we address this acute need by deriving from first principles an exact formula for when a Jekyll-and-Hyde tipping point o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20980","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/2504.20980/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":"2504.20980","created_at":"2026-07-05T10:55:52.387921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20980v1","created_at":"2026-07-05T10:55:52.387921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20980","created_at":"2026-07-05T10:55:52.387921+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJYPH4DBXJXN","created_at":"2026-07-05T10:55:52.387921+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJYPH4DBXJXN5QVS","created_at":"2026-07-05T10:55:52.387921+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJYPH4DB","created_at":"2026-07-05T10:55:52.387921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14218","citing_title":"Fusion-fission forecasts when AI will shift to undesirable behavior","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FJYPH4DBXJXN5QVS7BTPAZCC7Q","json":"https://pith.science/pith/FJYPH4DBXJXN5QVS7BTPAZCC7Q.json","graph_json":"https://pith.science/api/pith-number/FJYPH4DBXJXN5QVS7BTPAZCC7Q/graph.json","events_json":"https://pith.science/api/pith-number/FJYPH4DBXJXN5QVS7BTPAZCC7Q/events.json","paper":"https://pith.science/paper/FJYPH4DB"},"agent_actions":{"view_html":"https://pith.science/pith/FJYPH4DBXJXN5QVS7BTPAZCC7Q","download_json":"https://pith.science/pith/FJYPH4DBXJXN5QVS7BTPAZCC7Q.json","view_paper":"https://pith.science/paper/FJYPH4DB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20980&json=true","fetch_graph":"https://pith.science/api/pith-number/FJYPH4DBXJXN5QVS7BTPAZCC7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/FJYPH4DBXJXN5QVS7BTPAZCC7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJYPH4DBXJXN5QVS7BTPAZCC7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJYPH4DBXJXN5QVS7BTPAZCC7Q/action/storage_attestation","attest_author":"https://pith.science/pith/FJYPH4DBXJXN5QVS7BTPAZCC7Q/action/author_attestation","sign_citation":"https://pith.science/pith/FJYPH4DBXJXN5QVS7BTPAZCC7Q/action/citation_signature","submit_replication":"https://pith.science/pith/FJYPH4DBXJXN5QVS7BTPAZCC7Q/action/replication_record"}},"created_at":"2026-07-05T10:55:52.387921+00:00","updated_at":"2026-07-05T10:55:52.387921+00:00"}