{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FCQZZ675SU4IF2BVMIS2ILD6WR","short_pith_number":"pith:FCQZZ675","canonical_record":{"source":{"id":"1902.00715","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-02T13:22:35Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"bf92fa1bbe32d8d6e8823a84e83db20b93f9fa9d7dd5432252df2374e7721419","abstract_canon_sha256":"1631577d85d9a54bb23c6d910f61fb1fff697a412967b1033c573e1ec0ecfe61"},"schema_version":"1.0"},"canonical_sha256":"28a19cfbfd953882e8356225a42c7eb465a14b0008aac2754856831c89b18bcd","source":{"kind":"arxiv","id":"1902.00715","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00715","created_at":"2026-05-17T23:49:39Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00715v2","created_at":"2026-05-17T23:49:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00715","created_at":"2026-05-17T23:49:39Z"},{"alias_kind":"pith_short_12","alias_value":"FCQZZ675SU4I","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FCQZZ675SU4IF2BV","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FCQZZ675","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FCQZZ675SU4IF2BVMIS2ILD6WR","target":"record","payload":{"canonical_record":{"source":{"id":"1902.00715","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-02T13:22:35Z","cross_cats_sorted":["cs.IR","stat.ML"],"title_canon_sha256":"bf92fa1bbe32d8d6e8823a84e83db20b93f9fa9d7dd5432252df2374e7721419","abstract_canon_sha256":"1631577d85d9a54bb23c6d910f61fb1fff697a412967b1033c573e1ec0ecfe61"},"schema_version":"1.0"},"canonical_sha256":"28a19cfbfd953882e8356225a42c7eb465a14b0008aac2754856831c89b18bcd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:39.385341Z","signature_b64":"aGWsD8U0Fil27gEng6EZvCSNzCUQiJetzPDhh09lSoFzctsvYE8zOr/Ti22mcCwsFMVx+Kr3YVdsd1PMPMk0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a19cfbfd953882e8356225a42c7eb465a14b0008aac2754856831c89b18bcd","last_reissued_at":"2026-05-17T23:49:39.384815Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:39.384815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.00715","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":"2026-05-17T23:49:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fuv5Rj5EZseU+TqVrqRkdkakCfkLWtQN0pruwZarAIhyP7lyRG/9D6FyO8Zmgdbtw2sx4mM8sgziIS+B5mfPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:06:35.227583Z"},"content_sha256":"1928faac283818b80e224eb90b8584345922a2c9a0db0812e41295df2f82295e","schema_version":"1.0","event_id":"sha256:1928faac283818b80e224eb90b8584345922a2c9a0db0812e41295df2f82295e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FCQZZ675SU4IF2BVMIS2ILD6WR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Collaborative Filtering Meets Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Wenjie Li, Yu Lei","submitted_at":"2019-02-02T13:22:35Z","abstract_excerpt":"In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named CFRL, which seamlessly integrates the ideas of both collaborative filtering (CF) and reinforcement learning (RL). More specifically, we first model the recommender-user interactive recommendation problem as an agent-environment RL task, which is mathematically described by a Markov decision process (MDP). Further, to achieve collaborative recommendations for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00715","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":"2026-05-17T23:49:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yG7pXlkxEaOAP82vkfq4qPpuskb+k3qq0jm7YzIXhzgcfIQNoflffZkjKbVOYCcCJa5tvXXuhsg253MGnN2JCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:06:35.228112Z"},"content_sha256":"c84d9bf599f4ae6c82862c9d5b802d9353d30fb4dd6d6e9819d15ec76ba41487","schema_version":"1.0","event_id":"sha256:c84d9bf599f4ae6c82862c9d5b802d9353d30fb4dd6d6e9819d15ec76ba41487"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/bundle.json","state_url":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/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":"2026-05-30T09:06:35Z","links":{"resolver":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR","bundle":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/bundle.json","state":"https://pith.science/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FCQZZ675SU4IF2BVMIS2ILD6WR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FCQZZ675SU4IF2BVMIS2ILD6WR","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":"1631577d85d9a54bb23c6d910f61fb1fff697a412967b1033c573e1ec0ecfe61","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-02T13:22:35Z","title_canon_sha256":"bf92fa1bbe32d8d6e8823a84e83db20b93f9fa9d7dd5432252df2374e7721419"},"schema_version":"1.0","source":{"id":"1902.00715","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00715","created_at":"2026-05-17T23:49:39Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00715v2","created_at":"2026-05-17T23:49:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00715","created_at":"2026-05-17T23:49:39Z"},{"alias_kind":"pith_short_12","alias_value":"FCQZZ675SU4I","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FCQZZ675SU4IF2BV","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FCQZZ675","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:c84d9bf599f4ae6c82862c9d5b802d9353d30fb4dd6d6e9819d15ec76ba41487","target":"graph","created_at":"2026-05-17T23:49:39Z","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":"In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named CFRL, which seamlessly integrates the ideas of both collaborative filtering (CF) and reinforcement learning (RL). More specifically, we first model the recommender-user interactive recommendation problem as an agent-environment RL task, which is mathematically described by a Markov decision process (MDP). Further, to achieve collaborative recommendations for ","authors_text":"Wenjie Li, Yu Lei","cross_cats":["cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-02T13:22:35Z","title":"When Collaborative Filtering Meets Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00715","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":"sha256:1928faac283818b80e224eb90b8584345922a2c9a0db0812e41295df2f82295e","target":"record","created_at":"2026-05-17T23:49:39Z","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":"1631577d85d9a54bb23c6d910f61fb1fff697a412967b1033c573e1ec0ecfe61","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-02T13:22:35Z","title_canon_sha256":"bf92fa1bbe32d8d6e8823a84e83db20b93f9fa9d7dd5432252df2374e7721419"},"schema_version":"1.0","source":{"id":"1902.00715","kind":"arxiv","version":2}},"canonical_sha256":"28a19cfbfd953882e8356225a42c7eb465a14b0008aac2754856831c89b18bcd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28a19cfbfd953882e8356225a42c7eb465a14b0008aac2754856831c89b18bcd","first_computed_at":"2026-05-17T23:49:39.384815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:39.384815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aGWsD8U0Fil27gEng6EZvCSNzCUQiJetzPDhh09lSoFzctsvYE8zOr/Ti22mcCwsFMVx+Kr3YVdsd1PMPMk0Dg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:39.385341Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.00715","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1928faac283818b80e224eb90b8584345922a2c9a0db0812e41295df2f82295e","sha256:c84d9bf599f4ae6c82862c9d5b802d9353d30fb4dd6d6e9819d15ec76ba41487"],"state_sha256":"19428f91c6e83f13e9b85a47dcb205cb61446b87ff9f611720fdd9fa27cd1ce2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SOqDm3Px6cmsqH2PLzTyH5vknEQ82TlN86506gIb2rrDnVdXn7Uprj9Fy+6BaMvhQtl6SkipDp0mJNydEQI+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T09:06:35.230962Z","bundle_sha256":"3ae2089b7559faf8d78237dec315101468982d89f2b5e10d0d5fe2c52dd1c40d"}}