{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NBSNIDSPPTU55QWIR7MWWHKOXR","short_pith_number":"pith:NBSNIDSP","canonical_record":{"source":{"id":"2506.16753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T05:13:10Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"4178b018cabd03ebe7f4f65e0e71bc527f34d27f83cedb359df2c2051d8ea3c0","abstract_canon_sha256":"14c2a9732cdbce108b1fd05e2ebff8ae11c9ada76a192aa30d4c6a3f5b4265b6"},"schema_version":"1.0"},"canonical_sha256":"6864d40e4f7ce9dec2c88fd96b1d4ebc787eab0ba9f2da0c48c177d7d9a4f73a","source":{"kind":"arxiv","id":"2506.16753","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16753","created_at":"2026-07-05T11:24:42Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16753v1","created_at":"2026-07-05T11:24:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16753","created_at":"2026-07-05T11:24:42Z"},{"alias_kind":"pith_short_12","alias_value":"NBSNIDSPPTU5","created_at":"2026-07-05T11:24:42Z"},{"alias_kind":"pith_short_16","alias_value":"NBSNIDSPPTU55QWI","created_at":"2026-07-05T11:24:42Z"},{"alias_kind":"pith_short_8","alias_value":"NBSNIDSP","created_at":"2026-07-05T11:24:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NBSNIDSPPTU55QWIR7MWWHKOXR","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T05:13:10Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"4178b018cabd03ebe7f4f65e0e71bc527f34d27f83cedb359df2c2051d8ea3c0","abstract_canon_sha256":"14c2a9732cdbce108b1fd05e2ebff8ae11c9ada76a192aa30d4c6a3f5b4265b6"},"schema_version":"1.0"},"canonical_sha256":"6864d40e4f7ce9dec2c88fd96b1d4ebc787eab0ba9f2da0c48c177d7d9a4f73a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:42.225968Z","signature_b64":"ZkpcTxAwz71pSKGfS37DQbRwODUu/WU+o7YUhDxQv6iTDhkcc2En3tk3uV/8gfXir3RLQrofGt0T5LcXTcCICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6864d40e4f7ce9dec2c88fd96b1d4ebc787eab0ba9f2da0c48c177d7d9a4f73a","last_reissued_at":"2026-07-05T11:24:42.225568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:42.225568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16753","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":"2026-07-05T11:24:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z3urTcVoQXiUhfmQBhX5HgfIHi+PCaZTIS96Jsq/79uT7pmyEdcERtXMw7voWfkH0ZwS7zi4LbmgilGwl7/xAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:38:46.374599Z"},"content_sha256":"2b2e59607cc544e7ae3e943ec5c84f44c3e5c58742175796129190a791000f3f","schema_version":"1.0","event_id":"sha256:2b2e59607cc544e7ae3e943ec5c84f44c3e5c58742175796129190a791000f3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NBSNIDSPPTU55QWIR7MWWHKOXR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Akihiro Kubo, Kosuke Nakanishi, Shin Ishii, Yuji Yasui","submitted_at":"2025-06-20T05:13:10Z","abstract_excerpt":"Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable success, addressing worst-case scenarios over long time horizons requires both minimizing the agent's cumulative rewards for adversaries and training agents to counteract them through alternating learning. However, this process introduces mutual dependencies between the agent and the adversary, making interactions with the environment inefficient and hinderin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16753","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/2506.16753/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":"2026-07-05T11:24:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZjhDP9fH04li8rp6xCEoclOB+EaK0UDYNSX0t0+OBPQq4Fc3hq53YHjEIjHI545Lo+d8+4RFswtiCYHQ22MDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:38:46.375676Z"},"content_sha256":"206c92a11d988692d19a842d5f46f9f29c7c68cab3e3c6e98751d45725f53689","schema_version":"1.0","event_id":"sha256:206c92a11d988692d19a842d5f46f9f29c7c68cab3e3c6e98751d45725f53689"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBSNIDSPPTU55QWIR7MWWHKOXR/bundle.json","state_url":"https://pith.science/pith/NBSNIDSPPTU55QWIR7MWWHKOXR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBSNIDSPPTU55QWIR7MWWHKOXR/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":"2026-08-19T02:38:46Z","links":{"resolver":"https://pith.science/pith/NBSNIDSPPTU55QWIR7MWWHKOXR","bundle":"https://pith.science/pith/NBSNIDSPPTU55QWIR7MWWHKOXR/bundle.json","state":"https://pith.science/pith/NBSNIDSPPTU55QWIR7MWWHKOXR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBSNIDSPPTU55QWIR7MWWHKOXR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NBSNIDSPPTU55QWIR7MWWHKOXR","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":"14c2a9732cdbce108b1fd05e2ebff8ae11c9ada76a192aa30d4c6a3f5b4265b6","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T05:13:10Z","title_canon_sha256":"4178b018cabd03ebe7f4f65e0e71bc527f34d27f83cedb359df2c2051d8ea3c0"},"schema_version":"1.0","source":{"id":"2506.16753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16753","created_at":"2026-07-05T11:24:42Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16753v1","created_at":"2026-07-05T11:24:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16753","created_at":"2026-07-05T11:24:42Z"},{"alias_kind":"pith_short_12","alias_value":"NBSNIDSPPTU5","created_at":"2026-07-05T11:24:42Z"},{"alias_kind":"pith_short_16","alias_value":"NBSNIDSPPTU55QWI","created_at":"2026-07-05T11:24:42Z"},{"alias_kind":"pith_short_8","alias_value":"NBSNIDSP","created_at":"2026-07-05T11:24:42Z"}],"graph_snapshots":[{"event_id":"sha256:206c92a11d988692d19a842d5f46f9f29c7c68cab3e3c6e98751d45725f53689","target":"graph","created_at":"2026-07-05T11:24:42Z","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/2506.16753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable success, addressing worst-case scenarios over long time horizons requires both minimizing the agent's cumulative rewards for adversaries and training agents to counteract them through alternating learning. However, this process introduces mutual dependencies between the agent and the adversary, making interactions with the environment inefficient and hinderin","authors_text":"Akihiro Kubo, Kosuke Nakanishi, Shin Ishii, Yuji Yasui","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T05:13:10Z","title":"Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16753","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":"sha256:2b2e59607cc544e7ae3e943ec5c84f44c3e5c58742175796129190a791000f3f","target":"record","created_at":"2026-07-05T11:24:42Z","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":"14c2a9732cdbce108b1fd05e2ebff8ae11c9ada76a192aa30d4c6a3f5b4265b6","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-20T05:13:10Z","title_canon_sha256":"4178b018cabd03ebe7f4f65e0e71bc527f34d27f83cedb359df2c2051d8ea3c0"},"schema_version":"1.0","source":{"id":"2506.16753","kind":"arxiv","version":1}},"canonical_sha256":"6864d40e4f7ce9dec2c88fd96b1d4ebc787eab0ba9f2da0c48c177d7d9a4f73a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6864d40e4f7ce9dec2c88fd96b1d4ebc787eab0ba9f2da0c48c177d7d9a4f73a","first_computed_at":"2026-07-05T11:24:42.225568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:42.225568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZkpcTxAwz71pSKGfS37DQbRwODUu/WU+o7YUhDxQv6iTDhkcc2En3tk3uV/8gfXir3RLQrofGt0T5LcXTcCICw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:42.225968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b2e59607cc544e7ae3e943ec5c84f44c3e5c58742175796129190a791000f3f","sha256:206c92a11d988692d19a842d5f46f9f29c7c68cab3e3c6e98751d45725f53689"],"state_sha256":"3943a7d02248ea506302bf40308acd1d1cb50790a2f583abd2c88e4d543dc053"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LjbO81xkUq0tDV6vokuraYzYPpNM6KkEV+qJmrfncV6LfMNAIg4uPbYMmUiKeX0adiYn67aKZ8MrZsxvylY5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:38:46.382553Z","bundle_sha256":"367aa26ea5953398c9663554cef90249601b437465c39cb5ca63a872f608bdb2"}}