{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3YUKCG7JJDYRM4CHGQ2NV7ADCG","short_pith_number":"pith:3YUKCG7J","canonical_record":{"source":{"id":"2305.13747","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T07:04:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"700ed836e001a4208539b1bcbabc17c669882d2f9dccf50e8f56266cf660edca","abstract_canon_sha256":"2ad4d502650420aad3d527e41ff622dbad9fe1d8d41e88cdafd578b2c34df323"},"schema_version":"1.0"},"canonical_sha256":"de28a11be948f11670473434dafc031188eb7745c0c46442dcf90721b7a92205","source":{"kind":"arxiv","id":"2305.13747","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13747","created_at":"2026-07-05T06:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13747v3","created_at":"2026-07-05T06:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13747","created_at":"2026-07-05T06:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"3YUKCG7JJDYR","created_at":"2026-07-05T06:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"3YUKCG7JJDYRM4CH","created_at":"2026-07-05T06:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"3YUKCG7J","created_at":"2026-07-05T06:35:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3YUKCG7JJDYRM4CHGQ2NV7ADCG","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13747","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T07:04:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"700ed836e001a4208539b1bcbabc17c669882d2f9dccf50e8f56266cf660edca","abstract_canon_sha256":"2ad4d502650420aad3d527e41ff622dbad9fe1d8d41e88cdafd578b2c34df323"},"schema_version":"1.0"},"canonical_sha256":"de28a11be948f11670473434dafc031188eb7745c0c46442dcf90721b7a92205","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:51.529807Z","signature_b64":"+yZEme1ZRc6J1vJZGr0pp7xJU09J0siAofGTAMkhvPZTw4+0fT2JFv3My/DmHevcvueEEk1FZyR4t1kyUhGsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de28a11be948f11670473434dafc031188eb7745c0c46442dcf90721b7a92205","last_reissued_at":"2026-07-05T06:35:51.529438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:51.529438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13747","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":"2026-07-05T06:35:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ltaWirLLvYX0tHQbys34RPM1GA46WBvXow0kjIOIaH2F5W4O7exjKk5g6zBT364jt7YuMxBS6/F6f3e7ZTIOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:31:41.107231Z"},"content_sha256":"318e47588047bdac1a63bee46fedfd771b685c072632e182d63c03e6e224a291","schema_version":"1.0","event_id":"sha256:318e47588047bdac1a63bee46fedfd771b685c072632e182d63c03e6e224a291"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3YUKCG7JJDYRM4CHGQ2NV7ADCG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Long-term Value for Auction-Based Recommender Systems via On-Policy Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Alex Nikulkov, Dmytro Korenkevych, Fan Liu, Jalaj Bhandari, Ruiyang Xu, Yuchen He, Zheqing Zhu","submitted_at":"2023-05-23T07:04:38Z","abstract_excerpt":"Auction-based recommender systems are prevalent in online advertising platforms, but they are typically optimized to allocate recommendation slots based on immediate expected return metrics, neglecting the downstream effects of recommendations on user behavior. In this study, we employ reinforcement learning to optimize for long-term return metrics in an auction-based recommender system. Utilizing temporal difference learning, a fundamental reinforcement learning algorithm, we implement an one-step policy improvement approach that biases the system towards recommendations with higher long-term"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13747","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.13747/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":"2026-07-05T06:35:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kOHHH+NrI9uNod4HK1CYViuUxaN+vvIJ5kXc4UM8zmQWZMC8CI0EEO98CWOWxRwIacUnrSFfk35jrZrdFIeSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:31:41.107724Z"},"content_sha256":"ff462bc3e07ee5596712026955da68cf7132e184e21f5389dabb6f865a7ea180","schema_version":"1.0","event_id":"sha256:ff462bc3e07ee5596712026955da68cf7132e184e21f5389dabb6f865a7ea180"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YUKCG7JJDYRM4CHGQ2NV7ADCG/bundle.json","state_url":"https://pith.science/pith/3YUKCG7JJDYRM4CHGQ2NV7ADCG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YUKCG7JJDYRM4CHGQ2NV7ADCG/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":"2026-08-15T11:31:41Z","links":{"resolver":"https://pith.science/pith/3YUKCG7JJDYRM4CHGQ2NV7ADCG","bundle":"https://pith.science/pith/3YUKCG7JJDYRM4CHGQ2NV7ADCG/bundle.json","state":"https://pith.science/pith/3YUKCG7JJDYRM4CHGQ2NV7ADCG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YUKCG7JJDYRM4CHGQ2NV7ADCG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3YUKCG7JJDYRM4CHGQ2NV7ADCG","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":"2ad4d502650420aad3d527e41ff622dbad9fe1d8d41e88cdafd578b2c34df323","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T07:04:38Z","title_canon_sha256":"700ed836e001a4208539b1bcbabc17c669882d2f9dccf50e8f56266cf660edca"},"schema_version":"1.0","source":{"id":"2305.13747","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13747","created_at":"2026-07-05T06:35:51Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13747v3","created_at":"2026-07-05T06:35:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13747","created_at":"2026-07-05T06:35:51Z"},{"alias_kind":"pith_short_12","alias_value":"3YUKCG7JJDYR","created_at":"2026-07-05T06:35:51Z"},{"alias_kind":"pith_short_16","alias_value":"3YUKCG7JJDYRM4CH","created_at":"2026-07-05T06:35:51Z"},{"alias_kind":"pith_short_8","alias_value":"3YUKCG7J","created_at":"2026-07-05T06:35:51Z"}],"graph_snapshots":[{"event_id":"sha256:ff462bc3e07ee5596712026955da68cf7132e184e21f5389dabb6f865a7ea180","target":"graph","created_at":"2026-07-05T06:35:51Z","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/2305.13747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Auction-based recommender systems are prevalent in online advertising platforms, but they are typically optimized to allocate recommendation slots based on immediate expected return metrics, neglecting the downstream effects of recommendations on user behavior. In this study, we employ reinforcement learning to optimize for long-term return metrics in an auction-based recommender system. Utilizing temporal difference learning, a fundamental reinforcement learning algorithm, we implement an one-step policy improvement approach that biases the system towards recommendations with higher long-term","authors_text":"Alex Nikulkov, Dmytro Korenkevych, Fan Liu, Jalaj Bhandari, Ruiyang Xu, Yuchen He, Zheqing Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T07:04:38Z","title":"Optimizing Long-term Value for Auction-Based Recommender Systems via On-Policy Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13747","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":"sha256:318e47588047bdac1a63bee46fedfd771b685c072632e182d63c03e6e224a291","target":"record","created_at":"2026-07-05T06:35:51Z","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":"2ad4d502650420aad3d527e41ff622dbad9fe1d8d41e88cdafd578b2c34df323","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T07:04:38Z","title_canon_sha256":"700ed836e001a4208539b1bcbabc17c669882d2f9dccf50e8f56266cf660edca"},"schema_version":"1.0","source":{"id":"2305.13747","kind":"arxiv","version":3}},"canonical_sha256":"de28a11be948f11670473434dafc031188eb7745c0c46442dcf90721b7a92205","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de28a11be948f11670473434dafc031188eb7745c0c46442dcf90721b7a92205","first_computed_at":"2026-07-05T06:35:51.529438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:51.529438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+yZEme1ZRc6J1vJZGr0pp7xJU09J0siAofGTAMkhvPZTw4+0fT2JFv3My/DmHevcvueEEk1FZyR4t1kyUhGsDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:51.529807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13747","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:318e47588047bdac1a63bee46fedfd771b685c072632e182d63c03e6e224a291","sha256:ff462bc3e07ee5596712026955da68cf7132e184e21f5389dabb6f865a7ea180"],"state_sha256":"63c7b0e75ab58e66d683d31ce1e7c152b5e970e70f9d910d114e3ae58e97fe4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2M+7R3S6dAd/+hd98uK68liF0mUw93NIdoUteXKeZYObYQv3+qCyL1pT/vU1LByYrxDN6ElwHm9M2dlzXMfmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T11:31:41.113306Z","bundle_sha256":"a0ef274ea0686cd5c659f693a740704ecab457b80fab69664aa08e0c56c2dbde"}}