{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2KTYOH6LQLRTGGGASLFF3RQGYM","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":"6f8d3be6df182f1c65d3afb9aa59763fb4e024640110ef0a22b75287be825e75","cross_cats_sorted":["cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:28:33Z","title_canon_sha256":"2728c3caefc52995b39d83a376ff13505cd8bcfd24b16679b517c96d0645ac34"},"schema_version":"1.0","source":{"id":"2410.24096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24096","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24096v1","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24096","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"pith_short_12","alias_value":"2KTYOH6LQLRT","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"2KTYOH6LQLRTGGGA","created_at":"2026-07-05T09:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"2KTYOH6L","created_at":"2026-07-05T09:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:2b2d88e01c6be8007597c6ce7861db2de30b39569936cf1a97f65da02ee44ced","target":"graph","created_at":"2026-07-05T09:29:19Z","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/2410.24096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we propose a formal, model-agnostic meta-learning framework for safe reinforcement learning. Our framework is inspired by how parents safeguard their children across a progression of increasingly riskier tasks, imparting a sense of safety that is carried over from task to task. We model this as a meta-learning process where each task is synchronized with a safeguard that monitors safety and provides a reward signal to the agent. The safeguard is implemented as a finite-state machine based on a safety specification; the reward signal is formally shaped around this specification. T","authors_text":"Hiteshi Sharma, Hosein Hasanbeig, Nabil Omi, Siddhartha Sen, Sriram K. Rajamani","cross_cats":["cs.LO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:28:33Z","title":"Progressive Safeguards for Safe and Model-Agnostic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24096","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:b5d03aa618aad1f4469da3c2cf7eb3fd7e0881fb6783bea914b689b0192e1baf","target":"record","created_at":"2026-07-05T09:29:19Z","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":"6f8d3be6df182f1c65d3afb9aa59763fb4e024640110ef0a22b75287be825e75","cross_cats_sorted":["cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T16:28:33Z","title_canon_sha256":"2728c3caefc52995b39d83a376ff13505cd8bcfd24b16679b517c96d0645ac34"},"schema_version":"1.0","source":{"id":"2410.24096","kind":"arxiv","version":1}},"canonical_sha256":"d2a7871fcb82e33318c092ca5dc606c331d325549ccfa39f35053d30e1388446","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2a7871fcb82e33318c092ca5dc606c331d325549ccfa39f35053d30e1388446","first_computed_at":"2026-07-05T09:29:19.247542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:19.247542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gon98rIQJNVhM8AE+iRdi+O9AdzPdHUDmvrrGWku7uZNQ+6cXNv2ezhOJi9GDB9wihHdR/jkbAMxwI00vSAQBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:19.248083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.24096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5d03aa618aad1f4469da3c2cf7eb3fd7e0881fb6783bea914b689b0192e1baf","sha256:2b2d88e01c6be8007597c6ce7861db2de30b39569936cf1a97f65da02ee44ced"],"state_sha256":"11bfe34c80abb7f3a094372e506b65e68c7ddd4b6e663bc9398abd14d45648aa"}