{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VTVIALPTKH2YDOQR7MNYFAPV3T","short_pith_number":"pith:VTVIALPT","canonical_record":{"source":{"id":"2302.03328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-07T09:11:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"250f2def70b667ba0ea3c3b26b180f9b8e09cba2751e1e44fcd1fe210811b06c","abstract_canon_sha256":"e8c939702a9f45af04fff219194c975e634fbb498fbc4e5bd6a90cb0e32f9637"},"schema_version":"1.0"},"canonical_sha256":"acea802df351f581ba11fb1b8281f5dceb777d29a697ef67c685b7e192054799","source":{"kind":"arxiv","id":"2302.03328","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03328","created_at":"2026-07-05T05:49:44Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03328v2","created_at":"2026-07-05T05:49:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03328","created_at":"2026-07-05T05:49:44Z"},{"alias_kind":"pith_short_12","alias_value":"VTVIALPTKH2Y","created_at":"2026-07-05T05:49:44Z"},{"alias_kind":"pith_short_16","alias_value":"VTVIALPTKH2YDOQR","created_at":"2026-07-05T05:49:44Z"},{"alias_kind":"pith_short_8","alias_value":"VTVIALPT","created_at":"2026-07-05T05:49:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VTVIALPTKH2YDOQR7MNYFAPV3T","target":"record","payload":{"canonical_record":{"source":{"id":"2302.03328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-07T09:11:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"250f2def70b667ba0ea3c3b26b180f9b8e09cba2751e1e44fcd1fe210811b06c","abstract_canon_sha256":"e8c939702a9f45af04fff219194c975e634fbb498fbc4e5bd6a90cb0e32f9637"},"schema_version":"1.0"},"canonical_sha256":"acea802df351f581ba11fb1b8281f5dceb777d29a697ef67c685b7e192054799","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:44.141127Z","signature_b64":"U6YX0rQdp7hpbA+ChJoaUhxQps5oQTt9/vyMtN8VPPQFmEbW5B86hnrE8l4vnvjGDAiEn6DJ0K9hvQfahSa8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acea802df351f581ba11fb1b8281f5dceb777d29a697ef67c685b7e192054799","last_reissued_at":"2026-07-05T05:49:44.140661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:44.140661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.03328","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":"2026-07-05T05:49:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gC1Sm7Uuh61Nz9lUUvrU/k3SV7+BGiiQ3eNOlMd8ROkXPB4lsjFhCsQ8/Xi4oyZZMYSmWWyTNvefMcM+0RCUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:27:20.429680Z"},"content_sha256":"f90c441d0143b0568d44a04e55ec9537d785ff603c7e711c14dad82bfce8906e","schema_version":"1.0","event_id":"sha256:f90c441d0143b0568d44a04e55ec9537d785ff603c7e711c14dad82bfce8906e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VTVIALPTKH2YDOQR7MNYFAPV3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Recommendations with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Dayou Chen, Dong Zheng, Jiejie Tian, Jingtong Gao, Kun Gai, Peng Jiang, Qingpeng Cai, Shuchang Liu, Tonghao He, Xiangyu Zhao, Ziru Liu","submitted_at":"2023-02-07T09:11:17Z","abstract_excerpt":"In recent years, Multi-task Learning (MTL) has yielded immense success in Recommender System (RS) applications. However, current MTL-based recommendation models tend to disregard the session-wise patterns of user-item interactions because they are predominantly constructed based on item-wise datasets. Moreover, balancing multiple objectives has always been a challenge in this field, which is typically avoided via linear estimations in existing works. To address these issues, in this paper, we propose a Reinforcement Learning (RL) enhanced MTL framework, namely RMTL, to combine the losses of di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03328","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.03328/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T05:49:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPxk0PcOLyLPcMJm16rYFzQNoGp1n9MoF/ijhAbJXebq+uAwDqrdq2ANkPMH0sPF6ox9Nn1TY47Ili880qsJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:27:20.430171Z"},"content_sha256":"dd412f352bd8f7610a025f4a2fe042e1c9c9f59e6e81a666b71b1ef13967ce94","schema_version":"1.0","event_id":"sha256:dd412f352bd8f7610a025f4a2fe042e1c9c9f59e6e81a666b71b1ef13967ce94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTVIALPTKH2YDOQR7MNYFAPV3T/bundle.json","state_url":"https://pith.science/pith/VTVIALPTKH2YDOQR7MNYFAPV3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTVIALPTKH2YDOQR7MNYFAPV3T/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":"2026-08-06T20:27:20Z","links":{"resolver":"https://pith.science/pith/VTVIALPTKH2YDOQR7MNYFAPV3T","bundle":"https://pith.science/pith/VTVIALPTKH2YDOQR7MNYFAPV3T/bundle.json","state":"https://pith.science/pith/VTVIALPTKH2YDOQR7MNYFAPV3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTVIALPTKH2YDOQR7MNYFAPV3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VTVIALPTKH2YDOQR7MNYFAPV3T","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":"e8c939702a9f45af04fff219194c975e634fbb498fbc4e5bd6a90cb0e32f9637","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-07T09:11:17Z","title_canon_sha256":"250f2def70b667ba0ea3c3b26b180f9b8e09cba2751e1e44fcd1fe210811b06c"},"schema_version":"1.0","source":{"id":"2302.03328","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03328","created_at":"2026-07-05T05:49:44Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03328v2","created_at":"2026-07-05T05:49:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03328","created_at":"2026-07-05T05:49:44Z"},{"alias_kind":"pith_short_12","alias_value":"VTVIALPTKH2Y","created_at":"2026-07-05T05:49:44Z"},{"alias_kind":"pith_short_16","alias_value":"VTVIALPTKH2YDOQR","created_at":"2026-07-05T05:49:44Z"},{"alias_kind":"pith_short_8","alias_value":"VTVIALPT","created_at":"2026-07-05T05:49:44Z"}],"graph_snapshots":[{"event_id":"sha256:dd412f352bd8f7610a025f4a2fe042e1c9c9f59e6e81a666b71b1ef13967ce94","target":"graph","created_at":"2026-07-05T05:49:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.03328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, Multi-task Learning (MTL) has yielded immense success in Recommender System (RS) applications. However, current MTL-based recommendation models tend to disregard the session-wise patterns of user-item interactions because they are predominantly constructed based on item-wise datasets. Moreover, balancing multiple objectives has always been a challenge in this field, which is typically avoided via linear estimations in existing works. To address these issues, in this paper, we propose a Reinforcement Learning (RL) enhanced MTL framework, namely RMTL, to combine the losses of di","authors_text":"Dayou Chen, Dong Zheng, Jiejie Tian, Jingtong Gao, Kun Gai, Peng Jiang, Qingpeng Cai, Shuchang Liu, Tonghao He, Xiangyu Zhao, Ziru Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-07T09:11:17Z","title":"Multi-Task Recommendations with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03328","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:f90c441d0143b0568d44a04e55ec9537d785ff603c7e711c14dad82bfce8906e","target":"record","created_at":"2026-07-05T05:49:44Z","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":"e8c939702a9f45af04fff219194c975e634fbb498fbc4e5bd6a90cb0e32f9637","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-07T09:11:17Z","title_canon_sha256":"250f2def70b667ba0ea3c3b26b180f9b8e09cba2751e1e44fcd1fe210811b06c"},"schema_version":"1.0","source":{"id":"2302.03328","kind":"arxiv","version":2}},"canonical_sha256":"acea802df351f581ba11fb1b8281f5dceb777d29a697ef67c685b7e192054799","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acea802df351f581ba11fb1b8281f5dceb777d29a697ef67c685b7e192054799","first_computed_at":"2026-07-05T05:49:44.140661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:44.140661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U6YX0rQdp7hpbA+ChJoaUhxQps5oQTt9/vyMtN8VPPQFmEbW5B86hnrE8l4vnvjGDAiEn6DJ0K9hvQfahSa8BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:44.141127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03328","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f90c441d0143b0568d44a04e55ec9537d785ff603c7e711c14dad82bfce8906e","sha256:dd412f352bd8f7610a025f4a2fe042e1c9c9f59e6e81a666b71b1ef13967ce94"],"state_sha256":"0f321084010eb656165021c78dfa235bb9a8b1a5f6c8e0db06b86190fcbf361d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tKUxL+SKgWM0GM8A74ODnLYAKz5HMzG5qhFGstyGieBha0OBP4uEC2mjKcocU0OScmEPhD73drwuhI0pVHdoDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:27:20.433846Z","bundle_sha256":"11e6e41637ff57b17876740f248d0cce985680ad83366b35f6e036bd6ec9b853"}}