{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RB3ZOVRBXVJPC25FDBIILDCJTA","short_pith_number":"pith:RB3ZOVRB","canonical_record":{"source":{"id":"2307.00787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T07:05:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e129a2e3eed80cdc2bc76c9b96d05fd077dda25108b2ddbe9915b63dd1fb19e1","abstract_canon_sha256":"b2a06f95e2aaa7c192c986715ff7faaba3d500d7af492a55ef1b99fc0ec0eb79"},"schema_version":"1.0"},"canonical_sha256":"8877975621bd52f16ba51850858c499802f40fd1b8a2a64c58b628b6c851c1e8","source":{"kind":"arxiv","id":"2307.00787","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00787","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00787v1","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00787","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_12","alias_value":"RB3ZOVRBXVJP","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_16","alias_value":"RB3ZOVRBXVJPC25F","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_8","alias_value":"RB3ZOVRB","created_at":"2026-07-05T06:27:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RB3ZOVRBXVJPC25FDBIILDCJTA","target":"record","payload":{"canonical_record":{"source":{"id":"2307.00787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T07:05:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e129a2e3eed80cdc2bc76c9b96d05fd077dda25108b2ddbe9915b63dd1fb19e1","abstract_canon_sha256":"b2a06f95e2aaa7c192c986715ff7faaba3d500d7af492a55ef1b99fc0ec0eb79"},"schema_version":"1.0"},"canonical_sha256":"8877975621bd52f16ba51850858c499802f40fd1b8a2a64c58b628b6c851c1e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:27:00.507754Z","signature_b64":"+EYbOTs0kcSjLfQBgT43leJci7mK5n1rBjSeMAZClL/GeM5pgO/acQioh3rFaJ6rhG9TIaIingMlCgX0n7AQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8877975621bd52f16ba51850858c499802f40fd1b8a2a64c58b628b6c851c1e8","last_reissued_at":"2026-07-05T06:27:00.507275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:27:00.507275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.00787","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:27:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d/BMPf2U4RjkL99Hq9Y6CbNDFum4C2/dIjgtCsI+qUbXvkxz9R0Q9LaBqMZHdjNtESCMCZ5aEy9GOVe5ChIvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:27:01.819328Z"},"content_sha256":"ade273cc06c2257c3a80b82f8b3ac3a57e2881cf147d80a150a1bb073c39d928","schema_version":"1.0","event_id":"sha256:ade273cc06c2257c3a80b82f8b3ac3a57e2881cf147d80a150a1bb073c39d928"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RB3ZOVRBXVJPC25FDBIILDCJTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Shutdown Avoidance of Language Models in Textual Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Leon Lang, Simon Lermen, Teun van der Weij","submitted_at":"2023-07-03T07:05:59Z","abstract_excerpt":"Recently, there has been an increase in interest in evaluating large language models for emergent and dangerous capabilities. Importantly, agents could reason that in some scenarios their goal is better achieved if they are not turned off, which can lead to undesirable behaviors. In this paper, we investigate the potential of using toy textual scenarios to evaluate instrumental reasoning and shutdown avoidance in language models such as GPT-4 and Claude. Furthermore, we explore whether shutdown avoidance is merely a result of simple pattern matching between the dataset and the prompt or if it "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00787","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/2307.00787/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:27:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Vp0L2o4xoeh7FbfUwLpP8fXBGeW5aX0t+1wn9kddXJfiqaUIYz665loRiTJJTyW6Xd6R43LAu5LPHGHVHtHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:27:01.819706Z"},"content_sha256":"a91a8e166f92a7bf0617d7513843601d1911aec31d8d93d4b0b90df07f21ff4e","schema_version":"1.0","event_id":"sha256:a91a8e166f92a7bf0617d7513843601d1911aec31d8d93d4b0b90df07f21ff4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RB3ZOVRBXVJPC25FDBIILDCJTA/bundle.json","state_url":"https://pith.science/pith/RB3ZOVRBXVJPC25FDBIILDCJTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RB3ZOVRBXVJPC25FDBIILDCJTA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T19:27:01Z","links":{"resolver":"https://pith.science/pith/RB3ZOVRBXVJPC25FDBIILDCJTA","bundle":"https://pith.science/pith/RB3ZOVRBXVJPC25FDBIILDCJTA/bundle.json","state":"https://pith.science/pith/RB3ZOVRBXVJPC25FDBIILDCJTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RB3ZOVRBXVJPC25FDBIILDCJTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RB3ZOVRBXVJPC25FDBIILDCJTA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b2a06f95e2aaa7c192c986715ff7faaba3d500d7af492a55ef1b99fc0ec0eb79","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T07:05:59Z","title_canon_sha256":"e129a2e3eed80cdc2bc76c9b96d05fd077dda25108b2ddbe9915b63dd1fb19e1"},"schema_version":"1.0","source":{"id":"2307.00787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00787","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00787v1","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00787","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_12","alias_value":"RB3ZOVRBXVJP","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_16","alias_value":"RB3ZOVRBXVJPC25F","created_at":"2026-07-05T06:27:00Z"},{"alias_kind":"pith_short_8","alias_value":"RB3ZOVRB","created_at":"2026-07-05T06:27:00Z"}],"graph_snapshots":[{"event_id":"sha256:a91a8e166f92a7bf0617d7513843601d1911aec31d8d93d4b0b90df07f21ff4e","target":"graph","created_at":"2026-07-05T06:27:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.00787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been an increase in interest in evaluating large language models for emergent and dangerous capabilities. Importantly, agents could reason that in some scenarios their goal is better achieved if they are not turned off, which can lead to undesirable behaviors. In this paper, we investigate the potential of using toy textual scenarios to evaluate instrumental reasoning and shutdown avoidance in language models such as GPT-4 and Claude. Furthermore, we explore whether shutdown avoidance is merely a result of simple pattern matching between the dataset and the prompt or if it ","authors_text":"Leon Lang, Simon Lermen, Teun van der Weij","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T07:05:59Z","title":"Evaluating Shutdown Avoidance of Language Models in Textual Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00787","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ade273cc06c2257c3a80b82f8b3ac3a57e2881cf147d80a150a1bb073c39d928","target":"record","created_at":"2026-07-05T06:27:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b2a06f95e2aaa7c192c986715ff7faaba3d500d7af492a55ef1b99fc0ec0eb79","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T07:05:59Z","title_canon_sha256":"e129a2e3eed80cdc2bc76c9b96d05fd077dda25108b2ddbe9915b63dd1fb19e1"},"schema_version":"1.0","source":{"id":"2307.00787","kind":"arxiv","version":1}},"canonical_sha256":"8877975621bd52f16ba51850858c499802f40fd1b8a2a64c58b628b6c851c1e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8877975621bd52f16ba51850858c499802f40fd1b8a2a64c58b628b6c851c1e8","first_computed_at":"2026-07-05T06:27:00.507275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:27:00.507275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+EYbOTs0kcSjLfQBgT43leJci7mK5n1rBjSeMAZClL/GeM5pgO/acQioh3rFaJ6rhG9TIaIingMlCgX0n7AQDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:27:00.507754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.00787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ade273cc06c2257c3a80b82f8b3ac3a57e2881cf147d80a150a1bb073c39d928","sha256:a91a8e166f92a7bf0617d7513843601d1911aec31d8d93d4b0b90df07f21ff4e"],"state_sha256":"c1c22f2529114147ce82721ffd93069f45b348992896cd77c3ae526b4f397647"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/naoV1vr0aaC08zgK3Gd96tWtP2p61Yo/93q939OFkI/3+BcsAJENwD7aOwZmzcL+EBh1Z9oVNvM10jZ0X8bDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:27:01.821662Z","bundle_sha256":"e2a4d187577a2ac1474614114af96d1f596a413b887745bbed6fb0a7a2bd5432"}}