{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BSTLFRJYSVSFHGADXEIVRI56PN","short_pith_number":"pith:BSTLFRJY","canonical_record":{"source":{"id":"1801.00209","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-30T23:30:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"94e96c6b8263023065437dfcbdc8f0d23d87d09b5075f37634c368bbb0de4fcf","abstract_canon_sha256":"6fc3f4b96b6a3fc1fbc2aace4d02febc85b909047b2260972893c4b1d1c758e1"},"schema_version":"1.0"},"canonical_sha256":"0ca6b2c5389564539803b91158a3be7b7a0e8fae4857109400d408535ca0978b","source":{"kind":"arxiv","id":"1801.00209","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00209","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00209v3","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00209","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"BSTLFRJYSVSF","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BSTLFRJYSVSFHGAD","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BSTLFRJY","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BSTLFRJYSVSFHGADXEIVRI56PN","target":"record","payload":{"canonical_record":{"source":{"id":"1801.00209","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-30T23:30:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"94e96c6b8263023065437dfcbdc8f0d23d87d09b5075f37634c368bbb0de4fcf","abstract_canon_sha256":"6fc3f4b96b6a3fc1fbc2aace4d02febc85b909047b2260972893c4b1d1c758e1"},"schema_version":"1.0"},"canonical_sha256":"0ca6b2c5389564539803b91158a3be7b7a0e8fae4857109400d408535ca0978b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:08.849976Z","signature_b64":"uyUV+ZTdRRiN3OTxzj7Y4M1evVN/0zdMmppo7vLN2TajkeThWDnmJej2JhTz05lGTjUUrVVB/4pBSjId5cskCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ca6b2c5389564539803b91158a3be7b7a0e8fae4857109400d408535ca0978b","last_reissued_at":"2026-05-17T23:42:08.849357Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:08.849357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.00209","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":"2026-05-17T23:42:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rIt2MfsZsPKxo22hLr79UzOrAT++su+N6TuNoz/F+KoMfnni5fZhQHk2S0uGzTKtp2Uc+1U3KlEaMZqf7JT3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:22:50.017540Z"},"content_sha256":"5452e6a13781c84b6764124d4e5273e72a8654f8ec7a7ca7ac516e4ab62d1073","schema_version":"1.0","event_id":"sha256:5452e6a13781c84b6764124d4e5273e72a8654f8ec7a7ca7ac516e4ab62d1073"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BSTLFRJYSVSFHGADXEIVRI56PN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for List-wise Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dawei Yin, Jiliang Tang, Liang Zhang, Long Xia, Xiangyu Zhao, Zhuoye Ding","submitted_at":"2017-12-30T23:30:36Z","abstract_excerpt":"Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00209","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":"2026-05-17T23:42:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ddNLQXquEQ64CzPFVvJxTFQpauA29aqzsBTxgzBRkkDDmNg6GlO2OW8+rdnZe0A/NPeFxU4z6pQXWoBkjc2/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:22:50.017885Z"},"content_sha256":"b4d21b0f69837b7c2370d2d5b8e2d0bcae53bd57af37adbb52b7d196af4cbc46","schema_version":"1.0","event_id":"sha256:b4d21b0f69837b7c2370d2d5b8e2d0bcae53bd57af37adbb52b7d196af4cbc46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN/bundle.json","state_url":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BSTLFRJYSVSFHGADXEIVRI56PN/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":"2026-05-31T20:22:50Z","links":{"resolver":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN","bundle":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN/bundle.json","state":"https://pith.science/pith/BSTLFRJYSVSFHGADXEIVRI56PN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BSTLFRJYSVSFHGADXEIVRI56PN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BSTLFRJYSVSFHGADXEIVRI56PN","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":"6fc3f4b96b6a3fc1fbc2aace4d02febc85b909047b2260972893c4b1d1c758e1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-30T23:30:36Z","title_canon_sha256":"94e96c6b8263023065437dfcbdc8f0d23d87d09b5075f37634c368bbb0de4fcf"},"schema_version":"1.0","source":{"id":"1801.00209","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00209","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00209v3","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00209","created_at":"2026-05-17T23:42:08Z"},{"alias_kind":"pith_short_12","alias_value":"BSTLFRJYSVSF","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BSTLFRJYSVSFHGAD","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BSTLFRJY","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:b4d21b0f69837b7c2370d2d5b8e2d0bcae53bd57af37adbb52b7d196af4cbc46","target":"graph","created_at":"2026-05-17T23:42:08Z","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":"Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learn","authors_text":"Dawei Yin, Jiliang Tang, Liang Zhang, Long Xia, Xiangyu Zhao, Zhuoye Ding","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-30T23:30:36Z","title":"Deep Reinforcement Learning for List-wise Recommendations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.00209","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":"sha256:5452e6a13781c84b6764124d4e5273e72a8654f8ec7a7ca7ac516e4ab62d1073","target":"record","created_at":"2026-05-17T23:42:08Z","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":"6fc3f4b96b6a3fc1fbc2aace4d02febc85b909047b2260972893c4b1d1c758e1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-30T23:30:36Z","title_canon_sha256":"94e96c6b8263023065437dfcbdc8f0d23d87d09b5075f37634c368bbb0de4fcf"},"schema_version":"1.0","source":{"id":"1801.00209","kind":"arxiv","version":3}},"canonical_sha256":"0ca6b2c5389564539803b91158a3be7b7a0e8fae4857109400d408535ca0978b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ca6b2c5389564539803b91158a3be7b7a0e8fae4857109400d408535ca0978b","first_computed_at":"2026-05-17T23:42:08.849357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:08.849357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uyUV+ZTdRRiN3OTxzj7Y4M1evVN/0zdMmppo7vLN2TajkeThWDnmJej2JhTz05lGTjUUrVVB/4pBSjId5cskCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:08.849976Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.00209","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5452e6a13781c84b6764124d4e5273e72a8654f8ec7a7ca7ac516e4ab62d1073","sha256:b4d21b0f69837b7c2370d2d5b8e2d0bcae53bd57af37adbb52b7d196af4cbc46"],"state_sha256":"8ab1e69e7ef9a4d29674d04da803422f3c9fca969ceecac31cd6ef3611396423"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C6cCr2EiWfVHnfkFegrCI9f5WkUhRhnrKtG3A7j4nl0KgcOFpYPsIeMF3TmgNeDoYPEuI7p8FzENCqQCLLzmBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:22:50.020071Z","bundle_sha256":"da30b085e0c9e8e74e3aa5d1e0ec32daa0994f493bd8f0d483391375abd6f68c"}}