{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XZXTEEFOIN7QN3KAQJYDSPJTO6","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":"7e384665bb00fb7d8269822d1ea7509ee0d79d21a9172ec261424d392c70b0ed","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T13:47:21Z","title_canon_sha256":"ecbd762d44f9068e214d80a65ed2d0b42461538a15d7720e530428c93e663c92"},"schema_version":"1.0","source":{"id":"2405.18180","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18180","created_at":"2026-07-05T11:59:05Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18180v3","created_at":"2026-07-05T11:59:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18180","created_at":"2026-07-05T11:59:05Z"},{"alias_kind":"pith_short_12","alias_value":"XZXTEEFOIN7Q","created_at":"2026-07-05T11:59:05Z"},{"alias_kind":"pith_short_16","alias_value":"XZXTEEFOIN7QN3KA","created_at":"2026-07-05T11:59:05Z"},{"alias_kind":"pith_short_8","alias_value":"XZXTEEFO","created_at":"2026-07-05T11:59:05Z"}],"graph_snapshots":[{"event_id":"sha256:3734d7a9bbd341dc49adf2c8c39a6e12abedafb373fd2a43d899f6bb18c96345","target":"graph","created_at":"2026-07-05T11:59:05Z","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/2405.18180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Empowering safe exploration of reinforcement learning (RL) agents during training is a critical challenge towards their deployment in many real-world scenarios. When prior knowledge of the domain or task is unavailable, training RL agents in unknown, black-box environments presents an even greater safety risk. We introduce ADVICE (Adaptive Shielding with a Contrastive Autoencoder), a novel post-shielding technique that distinguishes safe and unsafe features of state-action pairs during training, and uses this knowledge to protect the RL agent from executing actions that yield likely hazardous ","authors_text":"Calum Imrie, Daniel Bethell, Radu Calinescu, Simos Gerasimou","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T13:47:21Z","title":"Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18180","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":"sha256:1f5625ed87f21c3854d7111197839f8b1070deaff1dd5f6fc2ebd3fc41b21c96","target":"record","created_at":"2026-07-05T11:59:05Z","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":"7e384665bb00fb7d8269822d1ea7509ee0d79d21a9172ec261424d392c70b0ed","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T13:47:21Z","title_canon_sha256":"ecbd762d44f9068e214d80a65ed2d0b42461538a15d7720e530428c93e663c92"},"schema_version":"1.0","source":{"id":"2405.18180","kind":"arxiv","version":3}},"canonical_sha256":"be6f3210ae437f06ed408270393d3377be4af80d9ec4a252e27b918e5cd8f797","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be6f3210ae437f06ed408270393d3377be4af80d9ec4a252e27b918e5cd8f797","first_computed_at":"2026-07-05T11:59:05.375834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:05.375834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sl/Wd0Nga1HD412vNjtBa6dCRmROIjFnigxpCqWgWE9maG9/qHc1wqlpECdNVtYht5vlpE9PfQFeY60dN6nlBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:05.376347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18180","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f5625ed87f21c3854d7111197839f8b1070deaff1dd5f6fc2ebd3fc41b21c96","sha256:3734d7a9bbd341dc49adf2c8c39a6e12abedafb373fd2a43d899f6bb18c96345"],"state_sha256":"bb2d5c872b02a9086a9a3e8b2694b884309ae17aaa00324413e2d42cf5fbb8d5"}