{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:73WFDIFVB6MSL6TXKXRQKAYMK5","short_pith_number":"pith:73WFDIFV","canonical_record":{"source":{"id":"2406.18062","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T04:49:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d843f5cbc82ddf1af927349697bcd791c033ea88cbf783a8f9971c84009049e9","abstract_canon_sha256":"ba6b6906af812f496374eb0a950251c934e36804975cbb97d319322f432fd3d1"},"schema_version":"1.0"},"canonical_sha256":"feec51a0b50f9925fa7755e305030c575a71baab448dc313a50966743bfd7f8a","source":{"kind":"arxiv","id":"2406.18062","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18062","created_at":"2026-07-05T08:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18062v1","created_at":"2026-07-05T08:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18062","created_at":"2026-07-05T08:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"73WFDIFVB6MS","created_at":"2026-07-05T08:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"73WFDIFVB6MSL6TX","created_at":"2026-07-05T08:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"73WFDIFV","created_at":"2026-07-05T08:36:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:73WFDIFVB6MSL6TXKXRQKAYMK5","target":"record","payload":{"canonical_record":{"source":{"id":"2406.18062","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T04:49:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d843f5cbc82ddf1af927349697bcd791c033ea88cbf783a8f9971c84009049e9","abstract_canon_sha256":"ba6b6906af812f496374eb0a950251c934e36804975cbb97d319322f432fd3d1"},"schema_version":"1.0"},"canonical_sha256":"feec51a0b50f9925fa7755e305030c575a71baab448dc313a50966743bfd7f8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:54.497964Z","signature_b64":"SgArmE9e7bjtHrmtrxm0kjuPcr7gNScsiIEJsObRKOqn6WcQXtplSKy51q6GWaDK0jQMzHT+mLz7B7Cx41BgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"feec51a0b50f9925fa7755e305030c575a71baab448dc313a50966743bfd7f8a","last_reissued_at":"2026-07-05T08:36:54.497473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:54.497473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.18062","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HUFDFBj1AaoumGTtn1eG/bce0sRDvVjV/v2+0pRCsleZEXnooz0m5+FJIJr1/CKBr6H7TsdZQu3QVdhMfTvBDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:55:50.683105Z"},"content_sha256":"b59f5ac35ad2b35dee1a9ba4b1ef7289f33408c574eb141056fce672db4c079b","schema_version":"1.0","event_id":"sha256:b59f5ac35ad2b35dee1a9ba4b1ef7289f33408c574eb141056fce672db4c079b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:73WFDIFVB6MSL6TXKXRQKAYMK5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chung-En Sun, Sicun Gao, Tsui-Wei Weng","submitted_at":"2024-06-26T04:49:03Z","abstract_excerpt":"Robustness remains a paramount concern in deep reinforcement learning (DRL), with randomized smoothing emerging as a key technique for enhancing this attribute. However, a notable gap exists in the performance of current smoothed DRL agents, often characterized by significantly low clean rewards and weak robustness. In response to this challenge, our study introduces innovative algorithms aimed at training effective smoothed robust DRL agents. We propose S-DQN and S-PPO, novel approaches that demonstrate remarkable improvements in clean rewards, empirical robustness, and robustness guarantee a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18062","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.18062/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0c1NpKcAabqsfsqjRuoTsPRLpQQ1dIV5Ny9X1fFlQrJKfXidnbYYsb98/z7P5A4nKsHGtYLDMkMYGlgcNiEcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:55:50.684239Z"},"content_sha256":"06a679b6916a5871edabf71cc4f585ea45af59405df8848750eb04d0d693a4a7","schema_version":"1.0","event_id":"sha256:06a679b6916a5871edabf71cc4f585ea45af59405df8848750eb04d0d693a4a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/73WFDIFVB6MSL6TXKXRQKAYMK5/bundle.json","state_url":"https://pith.science/pith/73WFDIFVB6MSL6TXKXRQKAYMK5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/73WFDIFVB6MSL6TXKXRQKAYMK5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T20:55:50Z","links":{"resolver":"https://pith.science/pith/73WFDIFVB6MSL6TXKXRQKAYMK5","bundle":"https://pith.science/pith/73WFDIFVB6MSL6TXKXRQKAYMK5/bundle.json","state":"https://pith.science/pith/73WFDIFVB6MSL6TXKXRQKAYMK5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/73WFDIFVB6MSL6TXKXRQKAYMK5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:73WFDIFVB6MSL6TXKXRQKAYMK5","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":"ba6b6906af812f496374eb0a950251c934e36804975cbb97d319322f432fd3d1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T04:49:03Z","title_canon_sha256":"d843f5cbc82ddf1af927349697bcd791c033ea88cbf783a8f9971c84009049e9"},"schema_version":"1.0","source":{"id":"2406.18062","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18062","created_at":"2026-07-05T08:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18062v1","created_at":"2026-07-05T08:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18062","created_at":"2026-07-05T08:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"73WFDIFVB6MS","created_at":"2026-07-05T08:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"73WFDIFVB6MSL6TX","created_at":"2026-07-05T08:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"73WFDIFV","created_at":"2026-07-05T08:36:54Z"}],"graph_snapshots":[{"event_id":"sha256:06a679b6916a5871edabf71cc4f585ea45af59405df8848750eb04d0d693a4a7","target":"graph","created_at":"2026-07-05T08:36:54Z","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/2406.18062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robustness remains a paramount concern in deep reinforcement learning (DRL), with randomized smoothing emerging as a key technique for enhancing this attribute. However, a notable gap exists in the performance of current smoothed DRL agents, often characterized by significantly low clean rewards and weak robustness. In response to this challenge, our study introduces innovative algorithms aimed at training effective smoothed robust DRL agents. We propose S-DQN and S-PPO, novel approaches that demonstrate remarkable improvements in clean rewards, empirical robustness, and robustness guarantee a","authors_text":"Chung-En Sun, Sicun Gao, Tsui-Wei Weng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T04:49:03Z","title":"Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18062","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:b59f5ac35ad2b35dee1a9ba4b1ef7289f33408c574eb141056fce672db4c079b","target":"record","created_at":"2026-07-05T08:36:54Z","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":"ba6b6906af812f496374eb0a950251c934e36804975cbb97d319322f432fd3d1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T04:49:03Z","title_canon_sha256":"d843f5cbc82ddf1af927349697bcd791c033ea88cbf783a8f9971c84009049e9"},"schema_version":"1.0","source":{"id":"2406.18062","kind":"arxiv","version":1}},"canonical_sha256":"feec51a0b50f9925fa7755e305030c575a71baab448dc313a50966743bfd7f8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"feec51a0b50f9925fa7755e305030c575a71baab448dc313a50966743bfd7f8a","first_computed_at":"2026-07-05T08:36:54.497473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:54.497473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SgArmE9e7bjtHrmtrxm0kjuPcr7gNScsiIEJsObRKOqn6WcQXtplSKy51q6GWaDK0jQMzHT+mLz7B7Cx41BgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:54.497964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18062","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b59f5ac35ad2b35dee1a9ba4b1ef7289f33408c574eb141056fce672db4c079b","sha256:06a679b6916a5871edabf71cc4f585ea45af59405df8848750eb04d0d693a4a7"],"state_sha256":"e0d4aa0d72a5ee9bde514dce1ce0e257e558acb8f4e848e7c2fff331a23110c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a0R5bD7nqFO9zRaoResue5UmfsYAyST6IdEliw0jcnWAmP5oWzjGiuzYHCrHPWaGw0SUVql7Kn1KXZdUFZRwBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:55:50.691379Z","bundle_sha256":"38e92c9a18d63e38b92875101dc18b62e2a62fac47db9a62b79f9f0b0801f182"}}