{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3453PNDKVN7J4PEB7ZV2EO6R4E","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":"4f169afb3a67448d3e7117fbde912c8ae401cab310451836f1d2f28307b32757","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-08-12T00:18:23Z","title_canon_sha256":"30db5d38d8c7f97e956ebc2ef1b54eca28262a7ed36f7f4d1a2d1648e115ff05"},"schema_version":"1.0","source":{"id":"2508.09224","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09224","created_at":"2026-07-05T11:53:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09224v1","created_at":"2026-07-05T11:53:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09224","created_at":"2026-07-05T11:53:10Z"},{"alias_kind":"pith_short_12","alias_value":"3453PNDKVN7J","created_at":"2026-07-05T11:53:10Z"},{"alias_kind":"pith_short_16","alias_value":"3453PNDKVN7J4PEB","created_at":"2026-07-05T11:53:10Z"},{"alias_kind":"pith_short_8","alias_value":"3453PNDK","created_at":"2026-07-05T11:53:10Z"}],"graph_snapshots":[{"event_id":"sha256:f252f812a2d292e81e4580a2e10d634be625720bb12bd7d6d20cd123ba890845","target":"graph","created_at":"2026-07-05T11:53:10Z","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/2508.09224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models used in ChatGPT have traditionally been trained to learn a refusal boundary: depending on the user's intent, the model is taught to either fully comply or outright refuse. While this is a strong mitigation for explicitly malicious prompts, focusing safety training on refusals can lead to brittleness for prompts with obscured user intent. Binary refusal boundaries are especially ill-suited for dual-use cases (such as biology or cybersecurity), where a user request can be answered safely at a high level, but in some cases can lead to malicious uplift if sufficiently detaile","authors_text":"Alec Helyar, Alex Beutel, Andrea Vallone, Anna-Luisa Brakman, Saachi Jain, Tina Sriskandarajah, Yuan Yuan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-08-12T00:18:23Z","title":"From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09224","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":"sha256:2faafb96230e0b115dce4a65e582aa66da0a0376fa78f1cec97d2815af6681fa","target":"record","created_at":"2026-07-05T11:53:10Z","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":"4f169afb3a67448d3e7117fbde912c8ae401cab310451836f1d2f28307b32757","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-08-12T00:18:23Z","title_canon_sha256":"30db5d38d8c7f97e956ebc2ef1b54eca28262a7ed36f7f4d1a2d1648e115ff05"},"schema_version":"1.0","source":{"id":"2508.09224","kind":"arxiv","version":1}},"canonical_sha256":"df3bb7b46aab7e9e3c81fe6ba23bd1e10a3a568d0cee3a6b544d9c22a88ee49c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df3bb7b46aab7e9e3c81fe6ba23bd1e10a3a568d0cee3a6b544d9c22a88ee49c","first_computed_at":"2026-07-05T11:53:10.470594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:10.470594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fAE5CZR3VvxJ4h9VmO4GFgMFfqEQM80L+cDUyk7hV30rpQwrT6XKhKbdNv7XefVg+oEVwigEbxdcuNu+d+gMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:10.471080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.09224","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2faafb96230e0b115dce4a65e582aa66da0a0376fa78f1cec97d2815af6681fa","sha256:f252f812a2d292e81e4580a2e10d634be625720bb12bd7d6d20cd123ba890845"],"state_sha256":"400eaba69e5bfe7840de909c9247b1a302cfc60105d4205e4882836060f2cdac"}