{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CIJF5WPABF5Q235VXL4RVCS554","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":"e18eaed317c8c0f424e02ed782c8aec673505e41a96cab742f8f2877af4b2835","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T05:26:28Z","title_canon_sha256":"fc7b562a11fe604196ec625a782c5a7bffae43874359578ec1b2be2ec06e5ff8"},"schema_version":"1.0","source":{"id":"2504.03185","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.03185","created_at":"2026-07-05T10:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"2504.03185v1","created_at":"2026-07-05T10:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03185","created_at":"2026-07-05T10:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"CIJF5WPABF5Q","created_at":"2026-07-05T10:44:27Z"},{"alias_kind":"pith_short_16","alias_value":"CIJF5WPABF5Q235V","created_at":"2026-07-05T10:44:27Z"},{"alias_kind":"pith_short_8","alias_value":"CIJF5WPA","created_at":"2026-07-05T10:44:27Z"}],"graph_snapshots":[{"event_id":"sha256:0bc97b98eb3e2a9b57b81e9870982b56f184b2e0808973a41d445e4eb900a709","target":"graph","created_at":"2026-07-05T10:44:27Z","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/2504.03185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee constraint satisfaction outside their training distribution due to their reliance on implicit, post-hoc preferences. Inspired by a paradigm shift to first curate data before tuning, we introduce a new framework for safe language alignment that learns natural language constraints from positive and negative demonstrations as a primary step. From inferring both a","authors_text":"Chen Wang, Jaymari Chua, Lina Yao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T05:26:28Z","title":"Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03185","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:bdd808ceb7b6e6ed3f1923faa68015c209a5c6c5fb8f99eb0bad10df1b836566","target":"record","created_at":"2026-07-05T10:44:27Z","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":"e18eaed317c8c0f424e02ed782c8aec673505e41a96cab742f8f2877af4b2835","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T05:26:28Z","title_canon_sha256":"fc7b562a11fe604196ec625a782c5a7bffae43874359578ec1b2be2ec06e5ff8"},"schema_version":"1.0","source":{"id":"2504.03185","kind":"arxiv","version":1}},"canonical_sha256":"12125ed9e0097b0d6fb5baf91a8a5def0c91fd0b8d189dc6f9a37178ef8d717f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12125ed9e0097b0d6fb5baf91a8a5def0c91fd0b8d189dc6f9a37178ef8d717f","first_computed_at":"2026-07-05T10:44:27.722020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:27.722020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tco2YWQoyJV1MD3/0hYTzoV98WsPp3IIOGX1WR0kSr+3TJr0TYEWDGcWFyMF6/Idd1eVR3b+lki3aBwQTvb3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:27.722485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.03185","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bdd808ceb7b6e6ed3f1923faa68015c209a5c6c5fb8f99eb0bad10df1b836566","sha256:0bc97b98eb3e2a9b57b81e9870982b56f184b2e0808973a41d445e4eb900a709"],"state_sha256":"6c73618d627e2b40021d84261af4c51e2fa0bf8d3d26ba346f3bd6de312e57a8"}