{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:X2SA4KXK27NECYWWLN36KNG6N7","short_pith_number":"pith:X2SA4KXK","canonical_record":{"source":{"id":"2210.16915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-30T18:32:02Z","cross_cats_sorted":[],"title_canon_sha256":"22ccdc4de660b8bab5aa3f8a234357e4bc17a37446940e9180f912d82ee9b20e","abstract_canon_sha256":"a0176caa8c38ce0702973040c1ff901205c05f630b563afabd4b17bfb4a5691e"},"schema_version":"1.0"},"canonical_sha256":"bea40e2aead7da4162d65b77e534de6fe19f003546f8165283e80e9b8ce61af5","source":{"kind":"arxiv","id":"2210.16915","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.16915","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"2210.16915v1","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16915","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"X2SA4KXK27NE","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_16","alias_value":"X2SA4KXK27NECYWW","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_8","alias_value":"X2SA4KXK","created_at":"2026-07-05T05:11:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:X2SA4KXK27NECYWWLN36KNG6N7","target":"record","payload":{"canonical_record":{"source":{"id":"2210.16915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-30T18:32:02Z","cross_cats_sorted":[],"title_canon_sha256":"22ccdc4de660b8bab5aa3f8a234357e4bc17a37446940e9180f912d82ee9b20e","abstract_canon_sha256":"a0176caa8c38ce0702973040c1ff901205c05f630b563afabd4b17bfb4a5691e"},"schema_version":"1.0"},"canonical_sha256":"bea40e2aead7da4162d65b77e534de6fe19f003546f8165283e80e9b8ce61af5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:52.444949Z","signature_b64":"VmWk40WpjKRzPFoK2kBxsqjvbpt5wEmwlQEiq/zkQ/5q3yuhblZoigubs1w4L+R10j2Hyf8RFT08xwoHxK7WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bea40e2aead7da4162d65b77e534de6fe19f003546f8165283e80e9b8ce61af5","last_reissued_at":"2026-07-05T05:11:52.444488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:52.444488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.16915","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":"2026-07-05T05:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"92Ru3SK5vsFTONG/u86ZrJnV39x36m0bjz2uc/XsWexBtsWpjbZ4jjhXG/Ugh3AxnwQ6GM74wo6oE85Sly8jAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:48:41.889703Z"},"content_sha256":"b08d4738f79a33a728a55e969ea95c96e56fbf70ef81ef5bf5818d25ac9593b0","schema_version":"1.0","event_id":"sha256:b08d4738f79a33a728a55e969ea95c96e56fbf70ef81ef5bf5818d25ac9593b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:X2SA4KXK27NECYWWLN36KNG6N7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Thanh H. Nguyen, The Viet Bui, Tien Mai","submitted_at":"2022-10-30T18:32:02Z","abstract_excerpt":"Recent research on vulnerabilities of deep reinforcement learning (RL) has shown that adversarial policies adopted by an adversary agent can influence a target RL agent (victim agent) to perform poorly in a multi-agent environment. In existing studies, adversarial policies are directly trained based on experiences of interacting with the victim agent. There is a key shortcoming of this approach; knowledge derived from historical interactions may not be properly generalized to unexplored policy regions of the victim agent, making the trained adversarial policy significantly less effective. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16915","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/2210.16915/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":"2026-07-05T05:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yb57A+wz8CxsWbY5s5/Wv4qBfzjcgQdFW5oNOj9uMNs0CPLb+1IqQI7qRz4xOiKbr5Q7KYtt81G91MAL5NO0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:48:41.890118Z"},"content_sha256":"b551f69ec2ced0fc56dff0ec2ddda234e99b547928d75034041a55eceda1edcd","schema_version":"1.0","event_id":"sha256:b551f69ec2ced0fc56dff0ec2ddda234e99b547928d75034041a55eceda1edcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7/bundle.json","state_url":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X2SA4KXK27NECYWWLN36KNG6N7/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":"2026-07-06T10:48:41Z","links":{"resolver":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7","bundle":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7/bundle.json","state":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X2SA4KXK27NECYWWLN36KNG6N7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:X2SA4KXK27NECYWWLN36KNG6N7","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":"a0176caa8c38ce0702973040c1ff901205c05f630b563afabd4b17bfb4a5691e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-30T18:32:02Z","title_canon_sha256":"22ccdc4de660b8bab5aa3f8a234357e4bc17a37446940e9180f912d82ee9b20e"},"schema_version":"1.0","source":{"id":"2210.16915","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.16915","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"2210.16915v1","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16915","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"X2SA4KXK27NE","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_16","alias_value":"X2SA4KXK27NECYWW","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_8","alias_value":"X2SA4KXK","created_at":"2026-07-05T05:11:52Z"}],"graph_snapshots":[{"event_id":"sha256:b551f69ec2ced0fc56dff0ec2ddda234e99b547928d75034041a55eceda1edcd","target":"graph","created_at":"2026-07-05T05:11:52Z","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/2210.16915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research on vulnerabilities of deep reinforcement learning (RL) has shown that adversarial policies adopted by an adversary agent can influence a target RL agent (victim agent) to perform poorly in a multi-agent environment. In existing studies, adversarial policies are directly trained based on experiences of interacting with the victim agent. There is a key shortcoming of this approach; knowledge derived from historical interactions may not be properly generalized to unexplored policy regions of the victim agent, making the trained adversarial policy significantly less effective. In t","authors_text":"Thanh H. Nguyen, The Viet Bui, Tien Mai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-30T18:32:02Z","title":"Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16915","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:b08d4738f79a33a728a55e969ea95c96e56fbf70ef81ef5bf5818d25ac9593b0","target":"record","created_at":"2026-07-05T05:11:52Z","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":"a0176caa8c38ce0702973040c1ff901205c05f630b563afabd4b17bfb4a5691e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-30T18:32:02Z","title_canon_sha256":"22ccdc4de660b8bab5aa3f8a234357e4bc17a37446940e9180f912d82ee9b20e"},"schema_version":"1.0","source":{"id":"2210.16915","kind":"arxiv","version":1}},"canonical_sha256":"bea40e2aead7da4162d65b77e534de6fe19f003546f8165283e80e9b8ce61af5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bea40e2aead7da4162d65b77e534de6fe19f003546f8165283e80e9b8ce61af5","first_computed_at":"2026-07-05T05:11:52.444488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:52.444488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VmWk40WpjKRzPFoK2kBxsqjvbpt5wEmwlQEiq/zkQ/5q3yuhblZoigubs1w4L+R10j2Hyf8RFT08xwoHxK7WDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:52.444949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.16915","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b08d4738f79a33a728a55e969ea95c96e56fbf70ef81ef5bf5818d25ac9593b0","sha256:b551f69ec2ced0fc56dff0ec2ddda234e99b547928d75034041a55eceda1edcd"],"state_sha256":"cdb6b7e840052a542899e1e35bc74e85565c9da70603124a47618551798e4371"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQsxG5bAGTBxvPfE1sFtYeqnC22gUduKaChsU+SsVaev3u0w6Cg+g1Vd1GBdVGaXpF314FB9XkxFTXRqwVGHAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:48:41.891986Z","bundle_sha256":"7d596360e9b0e0a7dc0f0f63960b2267d660ceea748c9cee95c2a0e38c73b563"}}