{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2U6KPEBJOQF66SQAGTP3OOU5BI","short_pith_number":"pith:2U6KPEBJ","canonical_record":{"source":{"id":"1808.05760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-17T05:25:29Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"7c80a2f16afa28b67fcc3bab0d3871a0548b3260d1f71ef93cd3c9ea94f990db","abstract_canon_sha256":"eb8e68e2457e468f8a55c4c61545cd2c24a3e46ace99c8072750b19a2faeaedd"},"schema_version":"1.0"},"canonical_sha256":"d53ca79029740bef4a0034dfb73a9d0a3244a7a83dfec845abb59a40f40f9343","source":{"kind":"arxiv","id":"1808.05760","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.05760","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"1808.05760v2","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05760","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"2U6KPEBJOQF6","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2U6KPEBJOQF66SQA","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2U6KPEBJ","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2U6KPEBJOQF66SQAGTP3OOU5BI","target":"record","payload":{"canonical_record":{"source":{"id":"1808.05760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-17T05:25:29Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"7c80a2f16afa28b67fcc3bab0d3871a0548b3260d1f71ef93cd3c9ea94f990db","abstract_canon_sha256":"eb8e68e2457e468f8a55c4c61545cd2c24a3e46ace99c8072750b19a2faeaedd"},"schema_version":"1.0"},"canonical_sha256":"d53ca79029740bef4a0034dfb73a9d0a3244a7a83dfec845abb59a40f40f9343","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:23.157467Z","signature_b64":"XAetEPdxAwJKj5tJ34/u28vpSoazOGxmWbNEFfjRzvFO2Hfr1ZK7l25AhGECz51PCpvvqDN/WUR+2XI6IpteBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d53ca79029740bef4a0034dfb73a9d0a3244a7a83dfec845abb59a40f40f9343","last_reissued_at":"2026-05-18T00:07:23.156944Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:23.156944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.05760","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GONqGV5zP5yqKdYBED2qZyPHEvndCJ/ALWF1ffxxdY8KNYG2u2LsXAOAxLP1taWeHiMcUn2yTzqjY32oF9SLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:52:42.412427Z"},"content_sha256":"082d2fbe5ea6dd2a0f1f37d20c26eb079915b7d3436dd40a59538d72af22e99d","schema_version":"1.0","event_id":"sha256:082d2fbe5ea6dd2a0f1f37d20c26eb079915b7d3436dd40a59538d72af22e99d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2U6KPEBJOQF66SQAGTP3OOU5BI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Poisoning Attacks in Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kwang-Sung Jun, Lihong Li, Xiaojin Zhu, Yuzhe Ma","submitted_at":"2018-08-17T05:25:29Z","abstract_excerpt":"We study offline data poisoning attacks in contextual bandits, a class of reinforcement learning problems with important applications in online recommendation and adaptive medical treatment, among others. We provide a general attack framework based on convex optimization and show that by slightly manipulating rewards in the data, an attacker can force the bandit algorithm to pull a target arm for a target contextual vector. The target arm and target contextual vector are both chosen by the attacker. That is, the attacker can hijack the behavior of a contextual bandit. We also investigate the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05760","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:07:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9KHnPBceiNPRlW09Iuq3qSc2v0+lzWa51swpUvystJJ3o8UlDA4LLYsfP/dN2VFbL+F5kJ9LagyxHAdCpD4tAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:52:42.412773Z"},"content_sha256":"870bbe98a691ae457bf52095b3378a303768749706c3d3d410fba4968e8de235","schema_version":"1.0","event_id":"sha256:870bbe98a691ae457bf52095b3378a303768749706c3d3d410fba4968e8de235"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/bundle.json","state_url":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/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":"2026-06-01T17:52:42Z","links":{"resolver":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI","bundle":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/bundle.json","state":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2U6KPEBJOQF66SQAGTP3OOU5BI","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":"eb8e68e2457e468f8a55c4c61545cd2c24a3e46ace99c8072750b19a2faeaedd","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-17T05:25:29Z","title_canon_sha256":"7c80a2f16afa28b67fcc3bab0d3871a0548b3260d1f71ef93cd3c9ea94f990db"},"schema_version":"1.0","source":{"id":"1808.05760","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.05760","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"arxiv_version","alias_value":"1808.05760v2","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05760","created_at":"2026-05-18T00:07:23Z"},{"alias_kind":"pith_short_12","alias_value":"2U6KPEBJOQF6","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2U6KPEBJOQF66SQA","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2U6KPEBJ","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:870bbe98a691ae457bf52095b3378a303768749706c3d3d410fba4968e8de235","target":"graph","created_at":"2026-05-18T00:07:23Z","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"},"paper":{"abstract_excerpt":"We study offline data poisoning attacks in contextual bandits, a class of reinforcement learning problems with important applications in online recommendation and adaptive medical treatment, among others. We provide a general attack framework based on convex optimization and show that by slightly manipulating rewards in the data, an attacker can force the bandit algorithm to pull a target arm for a target contextual vector. The target arm and target contextual vector are both chosen by the attacker. That is, the attacker can hijack the behavior of a contextual bandit. We also investigate the f","authors_text":"Kwang-Sung Jun, Lihong Li, Xiaojin Zhu, Yuzhe Ma","cross_cats":["cs.CR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-17T05:25:29Z","title":"Data Poisoning Attacks in Contextual Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05760","kind":"arxiv","version":2},"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":"sha256:082d2fbe5ea6dd2a0f1f37d20c26eb079915b7d3436dd40a59538d72af22e99d","target":"record","created_at":"2026-05-18T00:07:23Z","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":"eb8e68e2457e468f8a55c4c61545cd2c24a3e46ace99c8072750b19a2faeaedd","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-17T05:25:29Z","title_canon_sha256":"7c80a2f16afa28b67fcc3bab0d3871a0548b3260d1f71ef93cd3c9ea94f990db"},"schema_version":"1.0","source":{"id":"1808.05760","kind":"arxiv","version":2}},"canonical_sha256":"d53ca79029740bef4a0034dfb73a9d0a3244a7a83dfec845abb59a40f40f9343","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d53ca79029740bef4a0034dfb73a9d0a3244a7a83dfec845abb59a40f40f9343","first_computed_at":"2026-05-18T00:07:23.156944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:23.156944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XAetEPdxAwJKj5tJ34/u28vpSoazOGxmWbNEFfjRzvFO2Hfr1ZK7l25AhGECz51PCpvvqDN/WUR+2XI6IpteBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:23.157467Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.05760","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:082d2fbe5ea6dd2a0f1f37d20c26eb079915b7d3436dd40a59538d72af22e99d","sha256:870bbe98a691ae457bf52095b3378a303768749706c3d3d410fba4968e8de235"],"state_sha256":"decc51b595078bde35fe6da222b07661b2e933a59bf6dd2842941451e9b0a957"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHG6DEGzvLei6DGetjQTPpytcwxN9K+SpdpUliab3QUQzVHBCISOIfnmbX0lwT6Laje37c0NDoVmoq14zTXECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T17:52:42.414761Z","bundle_sha256":"86a34b69aabe095fad30f14243cfdf54311571ef55be0e3fb679574959e9bc42"}}