{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OC64QK3GYFQFAN6BELG3YNTWFS","short_pith_number":"pith:OC64QK3G","canonical_record":{"source":{"id":"1905.12767","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T22:55:28Z","cross_cats_sorted":["cs.AI","cs.IR","stat.ML"],"title_canon_sha256":"85b52c4472ee8cdceb175af5b0095b9a7eba1c11aaabd0a29153b34582d2c6c7","abstract_canon_sha256":"abeb1d01cb9b74b89a36b6b9496ed5e4900cb27923981895f559fd22fe1d6f5e"},"schema_version":"1.0"},"canonical_sha256":"70bdc82b66c1605037c122cdbc36762c90bef508bdb2ee9ba80521ee7ed665fd","source":{"kind":"arxiv","id":"1905.12767","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12767","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12767v2","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12767","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"pith_short_12","alias_value":"OC64QK3GYFQF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OC64QK3GYFQFAN6B","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OC64QK3G","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OC64QK3GYFQFAN6BELG3YNTWFS","target":"record","payload":{"canonical_record":{"source":{"id":"1905.12767","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T22:55:28Z","cross_cats_sorted":["cs.AI","cs.IR","stat.ML"],"title_canon_sha256":"85b52c4472ee8cdceb175af5b0095b9a7eba1c11aaabd0a29153b34582d2c6c7","abstract_canon_sha256":"abeb1d01cb9b74b89a36b6b9496ed5e4900cb27923981895f559fd22fe1d6f5e"},"schema_version":"1.0"},"canonical_sha256":"70bdc82b66c1605037c122cdbc36762c90bef508bdb2ee9ba80521ee7ed665fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:37.336080Z","signature_b64":"n4jpPw7/s7TEu3VZaHG1OcAY0gF2eQ1KSRWvD0OmFHFIq0IyBoNReiVHHY1vR+6ebdvfPc6h3vSvbYE1RgQvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70bdc82b66c1605037c122cdbc36762c90bef508bdb2ee9ba80521ee7ed665fd","last_reissued_at":"2026-05-17T23:44:37.335623Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:37.335623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.12767","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":"2026-05-17T23:44:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tQ9NvnGGJedXDIOKiE+98TgjgC9YUmwf0w9+sT3jNq8QMx7FrEqHWdVirBtZgddPPIp8aU/gunxpallwX2LjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:50:03.740848Z"},"content_sha256":"195df8fd23a4aa26984ede97601efdc9f76e1c8c9bebac4cd022caf25d23690b","schema_version":"1.0","event_id":"sha256:195df8fd23a4aa26984ede97601efdc9f76e1c8c9bebac4cd022caf25d23690b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OC64QK3GYFQFAN6BELG3YNTWFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Craig Boutilier, Eugene Ie, Heng-Tze Cheng, Jim McFadden, Jing Wang, Morgane Lustman, Paul Covington, Ritesh Agarwal, Rui Wu, Sanmit Narvekar, Tushar Chandra, Vihan Jain, Vince Gatto","submitted_at":"2019-05-29T22:55:28Z","abstract_excerpt":"Most practical recommender systems focus on estimating immediate user engagement without considering the long-term effects of recommendations on user behavior. Reinforcement learning (RL) methods offer the potential to optimize recommendations for long-term user engagement. However, since users are often presented with slates of multiple items - which may have interacting effects on user choice - methods are required to deal with the combinatorics of the RL action space. In this work, we address the challenge of making slate-based recommendations to optimize long-term value using RL. Our contr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12767","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":"2026-05-17T23:44:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VZoccm5wreqxMG3uUoSYQlr/XBXAgV9tdPKzJ83bciuYYS9ykb9Q/2CWZhcnXQ7N78zu/8VZTIz6kzNIGk1iCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:50:03.741679Z"},"content_sha256":"00c481ad5bdce312b50fe9c6ebfb0c7d126fa083b70745a5d334675cd9408168","schema_version":"1.0","event_id":"sha256:00c481ad5bdce312b50fe9c6ebfb0c7d126fa083b70745a5d334675cd9408168"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS/bundle.json","state_url":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OC64QK3GYFQFAN6BELG3YNTWFS/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":"2026-05-26T00:50:03Z","links":{"resolver":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS","bundle":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS/bundle.json","state":"https://pith.science/pith/OC64QK3GYFQFAN6BELG3YNTWFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OC64QK3GYFQFAN6BELG3YNTWFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OC64QK3GYFQFAN6BELG3YNTWFS","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":"abeb1d01cb9b74b89a36b6b9496ed5e4900cb27923981895f559fd22fe1d6f5e","cross_cats_sorted":["cs.AI","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T22:55:28Z","title_canon_sha256":"85b52c4472ee8cdceb175af5b0095b9a7eba1c11aaabd0a29153b34582d2c6c7"},"schema_version":"1.0","source":{"id":"1905.12767","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12767","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12767v2","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12767","created_at":"2026-05-17T23:44:37Z"},{"alias_kind":"pith_short_12","alias_value":"OC64QK3GYFQF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OC64QK3GYFQFAN6B","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OC64QK3G","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:00c481ad5bdce312b50fe9c6ebfb0c7d126fa083b70745a5d334675cd9408168","target":"graph","created_at":"2026-05-17T23:44:37Z","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":"Most practical recommender systems focus on estimating immediate user engagement without considering the long-term effects of recommendations on user behavior. Reinforcement learning (RL) methods offer the potential to optimize recommendations for long-term user engagement. However, since users are often presented with slates of multiple items - which may have interacting effects on user choice - methods are required to deal with the combinatorics of the RL action space. In this work, we address the challenge of making slate-based recommendations to optimize long-term value using RL. Our contr","authors_text":"Craig Boutilier, Eugene Ie, Heng-Tze Cheng, Jim McFadden, Jing Wang, Morgane Lustman, Paul Covington, Ritesh Agarwal, Rui Wu, Sanmit Narvekar, Tushar Chandra, Vihan Jain, Vince Gatto","cross_cats":["cs.AI","cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T22:55:28Z","title":"Reinforcement Learning for Slate-based Recommender Systems: A Tractable Decomposition and Practical Methodology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12767","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":"sha256:195df8fd23a4aa26984ede97601efdc9f76e1c8c9bebac4cd022caf25d23690b","target":"record","created_at":"2026-05-17T23:44:37Z","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":"abeb1d01cb9b74b89a36b6b9496ed5e4900cb27923981895f559fd22fe1d6f5e","cross_cats_sorted":["cs.AI","cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T22:55:28Z","title_canon_sha256":"85b52c4472ee8cdceb175af5b0095b9a7eba1c11aaabd0a29153b34582d2c6c7"},"schema_version":"1.0","source":{"id":"1905.12767","kind":"arxiv","version":2}},"canonical_sha256":"70bdc82b66c1605037c122cdbc36762c90bef508bdb2ee9ba80521ee7ed665fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70bdc82b66c1605037c122cdbc36762c90bef508bdb2ee9ba80521ee7ed665fd","first_computed_at":"2026-05-17T23:44:37.335623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:37.335623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n4jpPw7/s7TEu3VZaHG1OcAY0gF2eQ1KSRWvD0OmFHFIq0IyBoNReiVHHY1vR+6ebdvfPc6h3vSvbYE1RgQvBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:37.336080Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12767","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:195df8fd23a4aa26984ede97601efdc9f76e1c8c9bebac4cd022caf25d23690b","sha256:00c481ad5bdce312b50fe9c6ebfb0c7d126fa083b70745a5d334675cd9408168"],"state_sha256":"f1aaaec8f9ad5c0703ff1809377e69b4e79baa123caa89cbd23887bad913503f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4nbWYfQjk4uKbVtNghrkf6e3NGiYEVSim1fVAZymlSCGnfOjBUwBaYowa+a9QkndUM5AHy5ObLGmMZ8hSeKuCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:50:03.745273Z","bundle_sha256":"bae8edfc356545a7bf81995edba85827a40fe20d74fad6a4a4f05da0fef28628"}}