{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OD4YYGC7KGUTDJW25FWM2UAWEQ","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":"77771bb98fa9a1545bd8d859f11e2e84902ca9b4e4a2fc86e100e1175d34c0cc","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-03T17:50:06Z","title_canon_sha256":"74b594cede7482800a579a5bc01ab69e46dcf72aaac86616eb11619d006c3621"},"schema_version":"1.0","source":{"id":"2205.01663","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.01663","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"arxiv_version","alias_value":"2205.01663v5","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01663","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_12","alias_value":"OD4YYGC7KGUT","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_16","alias_value":"OD4YYGC7KGUTDJW2","created_at":"2026-07-05T05:14:57Z"},{"alias_kind":"pith_short_8","alias_value":"OD4YYGC7","created_at":"2026-07-05T05:14:57Z"}],"graph_snapshots":[{"event_id":"sha256:5acbcf46036ca40342a55afbce97e2540499f6a320cff9342def2f6303fc857c","target":"graph","created_at":"2026-07-05T05:14:57Z","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/2205.01663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to generate examples to train on in order to achieve better worst-case performance.\n  In this work, we used a safe language generation task (``avoid injuries'') as a testbed for achieving high reliability through adversarial training. We created a series of adversarial training techniques -- including a tool that assists human adversaries -- to find and eliminate f","authors_text":"Adam Scherlis, Ben Weinstein-Raun, Buck Shlegeris, Daniel de Haas, Daniel M. Ziegler, Lawrence Chan, Nate Thomas, Noa Nabeshima, Peter Schmidt-Nielsen, Seraphina Nix, Tao Lin, Tim Bauman","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-03T17:50:06Z","title":"Adversarial Training for High-Stakes Reliability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.01663","kind":"arxiv","version":5},"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:fc624d784748997ccdc52e7b93f778cd6269fe9c2c98db4078017aedba0092c5","target":"record","created_at":"2026-07-05T05:14:57Z","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":"77771bb98fa9a1545bd8d859f11e2e84902ca9b4e4a2fc86e100e1175d34c0cc","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-03T17:50:06Z","title_canon_sha256":"74b594cede7482800a579a5bc01ab69e46dcf72aaac86616eb11619d006c3621"},"schema_version":"1.0","source":{"id":"2205.01663","kind":"arxiv","version":5}},"canonical_sha256":"70f98c185f51a931a6dae96ccd50162428e53f975be4d46dd8284835b71316e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70f98c185f51a931a6dae96ccd50162428e53f975be4d46dd8284835b71316e3","first_computed_at":"2026-07-05T05:14:57.202844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:57.202844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z/1dY0PmLOut5vCHsETevcmkdSYsDmH6xwKKGnr2bT5pkD+a3dVHdPDzIoPmbAYO4fNu7r3VnQjfaQkClgSXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:57.203293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.01663","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc624d784748997ccdc52e7b93f778cd6269fe9c2c98db4078017aedba0092c5","sha256:5acbcf46036ca40342a55afbce97e2540499f6a320cff9342def2f6303fc857c"],"state_sha256":"5f17470d9b5a5447a3b60a697327874a3b956d03c70e494dda16547842c0c7a0"}