{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7E7IYP4PMSNHCEODMSD7XBHDN4","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":"c287c96b37cca252143b68ef14337071d73cc1b24aa29e98118efab34ba75b9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-17T14:06:05Z","title_canon_sha256":"613e8dd59f6aa6b9b9f94069eabb6f8d321d9469b86d55c6e8d62ca682e72382"},"schema_version":"1.0","source":{"id":"2311.10538","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.10538","created_at":"2026-07-05T07:19:23Z"},{"alias_kind":"arxiv_version","alias_value":"2311.10538v3","created_at":"2026-07-05T07:19:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10538","created_at":"2026-07-05T07:19:23Z"},{"alias_kind":"pith_short_12","alias_value":"7E7IYP4PMSNH","created_at":"2026-07-05T07:19:23Z"},{"alias_kind":"pith_short_16","alias_value":"7E7IYP4PMSNHCEOD","created_at":"2026-07-05T07:19:23Z"},{"alias_kind":"pith_short_8","alias_value":"7E7IYP4P","created_at":"2026-07-05T07:19:23Z"}],"graph_snapshots":[{"event_id":"sha256:ccc42e4c56f1f5b310719a04756fe3a64fa0a0d24db5221bf49cc8f0ff74948f","target":"graph","created_at":"2026-07-05T07:19:23Z","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/2311.10538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A prerequisite for safe autonomy-in-the-wild is safe testing-in-the-wild. Yet real-world autonomous tests face several unique safety challenges, both due to the possibility of causing harm during a test, as well as the risk of encountering new unsafe agent behavior through interactions with real-world and potentially malicious actors. We propose a framework for conducting safe autonomous agent tests on the open internet: agent actions are audited by a context-sensitive monitor that enforces a stringent safety boundary to stop an unsafe test, with suspect behavior ranked and logged to be examin","authors_text":"Adam Tauman Kalai, Craig Swift, David Atkinson, David Bau, Douglas Schonholtz, Marc Green, Merwane Hamadi, Silen Naihin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-17T14:06:05Z","title":"Testing Language Model Agents Safely in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10538","kind":"arxiv","version":3},"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":"sha256:4eeb8f35323d32b6b4ba22eba51ff863440578a99154a977dad531114258a26c","target":"record","created_at":"2026-07-05T07:19:23Z","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":"c287c96b37cca252143b68ef14337071d73cc1b24aa29e98118efab34ba75b9e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-17T14:06:05Z","title_canon_sha256":"613e8dd59f6aa6b9b9f94069eabb6f8d321d9469b86d55c6e8d62ca682e72382"},"schema_version":"1.0","source":{"id":"2311.10538","kind":"arxiv","version":3}},"canonical_sha256":"f93e8c3f8f649a7111c36487fb84e36f296152c8447283cff168bfa5d5598dbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f93e8c3f8f649a7111c36487fb84e36f296152c8447283cff168bfa5d5598dbc","first_computed_at":"2026-07-05T07:19:23.959007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:23.959007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EM/tDxZgZ6+YH9Gd2b2iLSllQCk+l4S9rj9DldWHCs2mwy7boeKHyGaJymY2sGbXE3k7DaQt+1WHAjUOfbu4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:23.959613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.10538","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4eeb8f35323d32b6b4ba22eba51ff863440578a99154a977dad531114258a26c","sha256:ccc42e4c56f1f5b310719a04756fe3a64fa0a0d24db5221bf49cc8f0ff74948f"],"state_sha256":"6a81d1f9bc02180d486d5c39e7dc91c2f6b80e8d74d0d4f997f409467ddd6efd"}