{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WST4OOM6S6IZV27YMPN3NYWZID","short_pith_number":"pith:WST4OOM6","canonical_record":{"source":{"id":"1802.06501","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-02-19T02:30:10Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e8cf92e2fd3dd6679cd0232c2c13f4e5e83dccbd0a5a3be7a782f50af9454639","abstract_canon_sha256":"69dc472cdc24752efb37bf81ee0349ddfaefe59896e47b970bc431abdda37c67"},"schema_version":"1.0"},"canonical_sha256":"b4a7c7399e97919aebf863dbb6e2d940d37609f10003e307d98b04820dc5e5cc","source":{"kind":"arxiv","id":"1802.06501","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06501","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06501v3","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06501","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"WST4OOM6S6IZ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WST4OOM6S6IZV27Y","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WST4OOM6","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WST4OOM6S6IZV27YMPN3NYWZID","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06501","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-02-19T02:30:10Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"e8cf92e2fd3dd6679cd0232c2c13f4e5e83dccbd0a5a3be7a782f50af9454639","abstract_canon_sha256":"69dc472cdc24752efb37bf81ee0349ddfaefe59896e47b970bc431abdda37c67"},"schema_version":"1.0"},"canonical_sha256":"b4a7c7399e97919aebf863dbb6e2d940d37609f10003e307d98b04820dc5e5cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:27.080047Z","signature_b64":"R6VS6qv750UQxgdk8MLVkYs5cFRhXQI0AK0VZROFKBiF/r+ZEVY9EHg9VePF+/nuaGnYsg82YoVoOGXwR1ELCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4a7c7399e97919aebf863dbb6e2d940d37609f10003e307d98b04820dc5e5cc","last_reissued_at":"2026-05-18T00:08:27.079607Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:27.079607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06501","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":"2026-05-18T00:08:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RdVV5pFQMOSHlMrM5OeEVnC53mSgHxyyBtjos0j9GNoSqjrisHiIK+f6B03cNMKeLHeOMxieWvffcqgNPB/4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:54:08.679851Z"},"content_sha256":"58d7133bbb6a69f37b74a69d34638b09e002c777f13ee26dd32ee451a7411989","schema_version":"1.0","event_id":"sha256:58d7133bbb6a69f37b74a69d34638b09e002c777f13ee26dd32ee451a7411989"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WST4OOM6S6IZV27YMPN3NYWZID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Dawei Yin, Jiliang Tang, Liang Zhang, Long Xia, Xiangyu Zhao, Zhuoye Ding","submitted_at":"2018-02-19T02:30:10Z","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":"1802.06501","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":"2026-05-18T00:08:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l0pMszuIOSoEhFdVMNyK1xyKXT4XrbBQzwmPB3tT+wG2QTku+B7h2ZeAFSjvpl/EY81Yh8BR8GzVQlWuREsDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T00:54:08.680189Z"},"content_sha256":"191872eb80bfffe332b9f4dc6d2fe3283638d3f5e8e4a6a5455014702dd56260","schema_version":"1.0","event_id":"sha256:191872eb80bfffe332b9f4dc6d2fe3283638d3f5e8e4a6a5455014702dd56260"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WST4OOM6S6IZV27YMPN3NYWZID/bundle.json","state_url":"https://pith.science/pith/WST4OOM6S6IZV27YMPN3NYWZID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WST4OOM6S6IZV27YMPN3NYWZID/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":"2026-06-09T00:54:08Z","links":{"resolver":"https://pith.science/pith/WST4OOM6S6IZV27YMPN3NYWZID","bundle":"https://pith.science/pith/WST4OOM6S6IZV27YMPN3NYWZID/bundle.json","state":"https://pith.science/pith/WST4OOM6S6IZV27YMPN3NYWZID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WST4OOM6S6IZV27YMPN3NYWZID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WST4OOM6S6IZV27YMPN3NYWZID","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":"69dc472cdc24752efb37bf81ee0349ddfaefe59896e47b970bc431abdda37c67","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-02-19T02:30:10Z","title_canon_sha256":"e8cf92e2fd3dd6679cd0232c2c13f4e5e83dccbd0a5a3be7a782f50af9454639"},"schema_version":"1.0","source":{"id":"1802.06501","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06501","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06501v3","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06501","created_at":"2026-05-18T00:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"WST4OOM6S6IZ","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WST4OOM6S6IZV27Y","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WST4OOM6","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:191872eb80bfffe332b9f4dc6d2fe3283638d3f5e8e4a6a5455014702dd56260","target":"graph","created_at":"2026-05-18T00:08:27Z","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":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-02-19T02:30:10Z","title":"Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06501","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":"sha256:58d7133bbb6a69f37b74a69d34638b09e002c777f13ee26dd32ee451a7411989","target":"record","created_at":"2026-05-18T00:08:27Z","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":"69dc472cdc24752efb37bf81ee0349ddfaefe59896e47b970bc431abdda37c67","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-02-19T02:30:10Z","title_canon_sha256":"e8cf92e2fd3dd6679cd0232c2c13f4e5e83dccbd0a5a3be7a782f50af9454639"},"schema_version":"1.0","source":{"id":"1802.06501","kind":"arxiv","version":3}},"canonical_sha256":"b4a7c7399e97919aebf863dbb6e2d940d37609f10003e307d98b04820dc5e5cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4a7c7399e97919aebf863dbb6e2d940d37609f10003e307d98b04820dc5e5cc","first_computed_at":"2026-05-18T00:08:27.079607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:27.079607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R6VS6qv750UQxgdk8MLVkYs5cFRhXQI0AK0VZROFKBiF/r+ZEVY9EHg9VePF+/nuaGnYsg82YoVoOGXwR1ELCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:27.080047Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06501","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58d7133bbb6a69f37b74a69d34638b09e002c777f13ee26dd32ee451a7411989","sha256:191872eb80bfffe332b9f4dc6d2fe3283638d3f5e8e4a6a5455014702dd56260"],"state_sha256":"85a148cce0455a59f66498bb394fe652a727bf3c7b299b74135b4bc29950dfa0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zYwBV/CNak7aX1+jVMNGdm/GkxNni6oyTzyrt0Fuj4FVN9Rd17cxzOiVASJdsuxvHJEPp7dUti6XhZ1Jntn+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T00:54:08.682045Z","bundle_sha256":"51f014d9721c2dbfd48068822daa63e38e30fd8c302e8b255468e207b93c3cee"}}