{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4SAPXMW7IH7FV3QED263PBNEOF","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":"474df8e672f129781015738f3e45f565b066b1653a339d7d3191bb6903547bf3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T10:16:46Z","title_canon_sha256":"235ec41776c9f047e8a18f636aa0d96bb3606412ce8f873e3fccfaeb4b5efcad"},"schema_version":"1.0","source":{"id":"2403.00420","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00420","created_at":"2026-06-10T01:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00420v3","created_at":"2026-06-10T01:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00420","created_at":"2026-06-10T01:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"4SAPXMW7IH7F","created_at":"2026-06-10T01:09:11Z"},{"alias_kind":"pith_short_16","alias_value":"4SAPXMW7IH7FV3QE","created_at":"2026-06-10T01:09:11Z"},{"alias_kind":"pith_short_8","alias_value":"4SAPXMW7","created_at":"2026-06-10T01:09:11Z"}],"graph_snapshots":[{"event_id":"sha256:1879d8fd4a0c359319e3922e82ee235f4f0cc7399e7dd6962c8ea2126e2a30fb","target":"graph","created_at":"2026-06-10T01:09:11Z","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/2403.00420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant performance in well-known environments, it remains susceptible to minor condition variations, raising concerns about its reliability in real-world applications. To improve usability, DRL must demonstrate trustworthiness and robustness. A way to improve the robustness of DRL to unknown changes in the environmental conditions and possible perturbations is through Adversarial Training, by training the agent against wel","authors_text":"Elies Gherbi, Frederic Cuppens, Hatem Hajri, Josephine Delas, Lucas Schott, Nora Boulahia-Cuppens, Reda Yaich, Sylvain Lamprier","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T10:16:46Z","title":"Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00420","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":"sha256:0ef660636be33b09774b5c2964af2a7f47decc200a4668b342ddf55ab87036fb","target":"record","created_at":"2026-06-10T01:09:11Z","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":"474df8e672f129781015738f3e45f565b066b1653a339d7d3191bb6903547bf3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T10:16:46Z","title_canon_sha256":"235ec41776c9f047e8a18f636aa0d96bb3606412ce8f873e3fccfaeb4b5efcad"},"schema_version":"1.0","source":{"id":"2403.00420","kind":"arxiv","version":3}},"canonical_sha256":"e480fbb2df41fe5aee041ebdb785a4717028c47db7818936abe1440f99daac19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e480fbb2df41fe5aee041ebdb785a4717028c47db7818936abe1440f99daac19","first_computed_at":"2026-06-10T01:09:11.257697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:11.257697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hIcpMKbhqNgGGwKVfFamVFSWucIGaM9vO+2QFguYSPT/0aC7kdU6z44UxXb8TXAKiebRbTvEF6A0iObL+vg8Cg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:11.258968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00420","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ef660636be33b09774b5c2964af2a7f47decc200a4668b342ddf55ab87036fb","sha256:1879d8fd4a0c359319e3922e82ee235f4f0cc7399e7dd6962c8ea2126e2a30fb"],"state_sha256":"6664987a977cfc4bd83329e6137882651dcc327a8c697776895a4d7cecc8dc4b"}