{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2JCS5VJQTQV5EF6Y5LMQOHVLE6","short_pith_number":"pith:2JCS5VJQ","schema_version":"1.0","canonical_sha256":"d2452ed5309c2bd217d8ead9071eab27bd46cabe4fd330376c65d7b6c232d6d2","source":{"kind":"arxiv","id":"2302.03561","version":3},"attestation_state":"computed","paper":{"title":"Optimizing Audio Recommendations for the Long-Term: A Reinforcement Learning Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Russo, Lucas Maystre, Yu Zhao","submitted_at":"2023-02-07T16:17:25Z","abstract_excerpt":"We present a novel podcast recommender system deployed at industrial scale. This system successfully optimizes personal listening journeys that unfold over months for hundreds of millions of listeners. In deviating from the pervasive industry practice of optimizing machine learning algorithms for short-term proxy metrics, the system substantially improves long-term performance in A/B tests. The paper offers insights into how our methods cope with attribution, coordination, and measurement challenges that usually hinder such long-term optimization. To contextualize these practical insights with"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.03561","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-07T16:17:25Z","cross_cats_sorted":["cs.AI","cs.IR","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"9c078a3ab6a05b36388ce7e220cc417d5594a467e8039837c4ef9ae38a63836f","abstract_canon_sha256":"6f02e64300ef993283456e5ba647ba39f82bfa6baf26c1f7f7465071e0e23115"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:23.741747Z","signature_b64":"R+GpwvZrDhGZHc/sMXqzztciyi0ECcaM2k9DRZ74Umhc1zzkguPcRjAJBHhmJl7QSN1359r1npmor+2G3Ma6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2452ed5309c2bd217d8ead9071eab27bd46cabe4fd330376c65d7b6c232d6d2","last_reissued_at":"2026-07-05T08:49:23.741342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:23.741342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Audio Recommendations for the Long-Term: A Reinforcement Learning Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Russo, Lucas Maystre, Yu Zhao","submitted_at":"2023-02-07T16:17:25Z","abstract_excerpt":"We present a novel podcast recommender system deployed at industrial scale. This system successfully optimizes personal listening journeys that unfold over months for hundreds of millions of listeners. In deviating from the pervasive industry practice of optimizing machine learning algorithms for short-term proxy metrics, the system substantially improves long-term performance in A/B tests. The paper offers insights into how our methods cope with attribution, coordination, and measurement challenges that usually hinder such long-term optimization. To contextualize these practical insights with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03561","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/2302.03561/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.03561","created_at":"2026-07-05T08:49:23.741399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03561v3","created_at":"2026-07-05T08:49:23.741399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03561","created_at":"2026-07-05T08:49:23.741399+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JCS5VJQTQV5","created_at":"2026-07-05T08:49:23.741399+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JCS5VJQTQV5EF6Y","created_at":"2026-07-05T08:49:23.741399+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JCS5VJQ","created_at":"2026-07-05T08:49:23.741399+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07761","citing_title":"Impatient Bandits: Optimizing for the Long-Term Without Delay","ref_index":2015,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JCS5VJQTQV5EF6Y5LMQOHVLE6","json":"https://pith.science/pith/2JCS5VJQTQV5EF6Y5LMQOHVLE6.json","graph_json":"https://pith.science/api/pith-number/2JCS5VJQTQV5EF6Y5LMQOHVLE6/graph.json","events_json":"https://pith.science/api/pith-number/2JCS5VJQTQV5EF6Y5LMQOHVLE6/events.json","paper":"https://pith.science/paper/2JCS5VJQ"},"agent_actions":{"view_html":"https://pith.science/pith/2JCS5VJQTQV5EF6Y5LMQOHVLE6","download_json":"https://pith.science/pith/2JCS5VJQTQV5EF6Y5LMQOHVLE6.json","view_paper":"https://pith.science/paper/2JCS5VJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03561&json=true","fetch_graph":"https://pith.science/api/pith-number/2JCS5VJQTQV5EF6Y5LMQOHVLE6/graph.json","fetch_events":"https://pith.science/api/pith-number/2JCS5VJQTQV5EF6Y5LMQOHVLE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JCS5VJQTQV5EF6Y5LMQOHVLE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JCS5VJQTQV5EF6Y5LMQOHVLE6/action/storage_attestation","attest_author":"https://pith.science/pith/2JCS5VJQTQV5EF6Y5LMQOHVLE6/action/author_attestation","sign_citation":"https://pith.science/pith/2JCS5VJQTQV5EF6Y5LMQOHVLE6/action/citation_signature","submit_replication":"https://pith.science/pith/2JCS5VJQTQV5EF6Y5LMQOHVLE6/action/replication_record"}},"created_at":"2026-07-05T08:49:23.741399+00:00","updated_at":"2026-07-05T08:49:23.741399+00:00"}