{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EO6YNBPXWOUVGJUTCPHTTMTWC7","short_pith_number":"pith:EO6YNBPX","canonical_record":{"source":{"id":"1802.04162","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T16:13:29Z","cross_cats_sorted":[],"title_canon_sha256":"23f5abf9607e73e8b51a7f626140c41307086ef0fa523e0fdb4088236c3f932d","abstract_canon_sha256":"15030a18b6c64405c36af46724491267613a6507b20e5c9ea4163a4f18836800"},"schema_version":"1.0"},"canonical_sha256":"23bd8685f7b3a953269313cf39b27617efa4c3303a6b00946d3933643d24e8f9","source":{"kind":"arxiv","id":"1802.04162","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04162","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04162v3","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04162","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"EO6YNBPXWOUV","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EO6YNBPXWOUVGJUT","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EO6YNBPX","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EO6YNBPXWOUVGJUTCPHTTMTWC7","target":"record","payload":{"canonical_record":{"source":{"id":"1802.04162","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T16:13:29Z","cross_cats_sorted":[],"title_canon_sha256":"23f5abf9607e73e8b51a7f626140c41307086ef0fa523e0fdb4088236c3f932d","abstract_canon_sha256":"15030a18b6c64405c36af46724491267613a6507b20e5c9ea4163a4f18836800"},"schema_version":"1.0"},"canonical_sha256":"23bd8685f7b3a953269313cf39b27617efa4c3303a6b00946d3933643d24e8f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:09.492951Z","signature_b64":"KunnlhlgYwJqpDs5mBmoL2ZM/05JPm6hXMHHRLGZMpopBDgqPDESrhv1DRW2kM92/8OYL/sE8Qdq2Pbc4cGQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23bd8685f7b3a953269313cf39b27617efa4c3303a6b00946d3933643d24e8f9","last_reissued_at":"2026-05-17T23:52:09.492338Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:09.492338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.04162","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bjxO5RQQtiVJCtpdQI1oyWo7V24wSVjYmQ/AVexV5IFp4gbXiEMElqq/aTJ1+BvpIZu11BOQCQyMKy6akD4dCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:15:29.020181Z"},"content_sha256":"905e45472b1f4769d070a27df224e8ef31acb3557adb3fbf6821962b7bb324e2","schema_version":"1.0","event_id":"sha256:905e45472b1f4769d070a27df224e8ef31acb3557adb3fbf6821962b7bb324e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EO6YNBPXWOUVGJUTCPHTTMTWC7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Gradients for Contextual Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feiyang Pan, Fuzhen Zhuang, Pingzhong Tang, Qing He, Qingpeng Cai","submitted_at":"2018-02-12T16:13:29Z","abstract_excerpt":"Decision making is a challenging task in online recommender systems. The decision maker often needs to choose a contextual item at each step from a set of candidates. Contextual bandit algorithms have been successfully deployed to such applications, for the trade-off between exploration and exploitation and the state-of-art performance on minimizing online costs. However, the applicability of existing contextual bandit methods is limited by the over-simplified assumptions of the problem, such as assuming a simple form of the reward function or assuming a static environment where the states are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04162","kind":"arxiv","version":3},"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":"2026-05-17T23:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5iRQ2R2o6GtOP8K8csQeAgDRyh7pFYB2+5j1TY5iIEbKOYwU2RpqZdKHpDvDQGHfEXASPYC4uLFRa1tBW4GnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:15:29.020587Z"},"content_sha256":"d2320e65f46b981394f7711e2172051a40a9a3955943942fd2c32ced52c6555a","schema_version":"1.0","event_id":"sha256:d2320e65f46b981394f7711e2172051a40a9a3955943942fd2c32ced52c6555a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EO6YNBPXWOUVGJUTCPHTTMTWC7/bundle.json","state_url":"https://pith.science/pith/EO6YNBPXWOUVGJUTCPHTTMTWC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EO6YNBPXWOUVGJUTCPHTTMTWC7/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":"2026-06-01T16:15:29Z","links":{"resolver":"https://pith.science/pith/EO6YNBPXWOUVGJUTCPHTTMTWC7","bundle":"https://pith.science/pith/EO6YNBPXWOUVGJUTCPHTTMTWC7/bundle.json","state":"https://pith.science/pith/EO6YNBPXWOUVGJUTCPHTTMTWC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EO6YNBPXWOUVGJUTCPHTTMTWC7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EO6YNBPXWOUVGJUTCPHTTMTWC7","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":"15030a18b6c64405c36af46724491267613a6507b20e5c9ea4163a4f18836800","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T16:13:29Z","title_canon_sha256":"23f5abf9607e73e8b51a7f626140c41307086ef0fa523e0fdb4088236c3f932d"},"schema_version":"1.0","source":{"id":"1802.04162","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.04162","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"1802.04162v3","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04162","created_at":"2026-05-17T23:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"EO6YNBPXWOUV","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EO6YNBPXWOUVGJUT","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EO6YNBPX","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:d2320e65f46b981394f7711e2172051a40a9a3955943942fd2c32ced52c6555a","target":"graph","created_at":"2026-05-17T23:52:09Z","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":"Decision making is a challenging task in online recommender systems. The decision maker often needs to choose a contextual item at each step from a set of candidates. Contextual bandit algorithms have been successfully deployed to such applications, for the trade-off between exploration and exploitation and the state-of-art performance on minimizing online costs. However, the applicability of existing contextual bandit methods is limited by the over-simplified assumptions of the problem, such as assuming a simple form of the reward function or assuming a static environment where the states are","authors_text":"Feiyang Pan, Fuzhen Zhuang, Pingzhong Tang, Qing He, Qingpeng Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T16:13:29Z","title":"Policy Gradients for Contextual Recommendations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04162","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":"sha256:905e45472b1f4769d070a27df224e8ef31acb3557adb3fbf6821962b7bb324e2","target":"record","created_at":"2026-05-17T23:52:09Z","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":"15030a18b6c64405c36af46724491267613a6507b20e5c9ea4163a4f18836800","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T16:13:29Z","title_canon_sha256":"23f5abf9607e73e8b51a7f626140c41307086ef0fa523e0fdb4088236c3f932d"},"schema_version":"1.0","source":{"id":"1802.04162","kind":"arxiv","version":3}},"canonical_sha256":"23bd8685f7b3a953269313cf39b27617efa4c3303a6b00946d3933643d24e8f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23bd8685f7b3a953269313cf39b27617efa4c3303a6b00946d3933643d24e8f9","first_computed_at":"2026-05-17T23:52:09.492338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:09.492338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KunnlhlgYwJqpDs5mBmoL2ZM/05JPm6hXMHHRLGZMpopBDgqPDESrhv1DRW2kM92/8OYL/sE8Qdq2Pbc4cGQAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:09.492951Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.04162","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:905e45472b1f4769d070a27df224e8ef31acb3557adb3fbf6821962b7bb324e2","sha256:d2320e65f46b981394f7711e2172051a40a9a3955943942fd2c32ced52c6555a"],"state_sha256":"ff1fa939f972d25399b74c7a8e9c2916510321bcc29426dacb844a083e41e037"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ydiTOoEH9jTaUUXyALLaRZt4J44zUIl2U0jtMSOa9nOSF1vV6JYt+q2v+jVGlna2U+gWOhFJDu+thO9POO+JBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T16:15:29.022606Z","bundle_sha256":"7d691dcd696cfb7b32725410bee90a2fdb9d939b86534cc34f741da6d0306212"}}