{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:STAOABRLMVOYMJ5OBLH5EPHIZ6","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":"e1c249c287792ae70393029d8a7f780cc1ffff4658e35817bb2544d98a56e697","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T00:28:26Z","title_canon_sha256":"6e7a22fa07a37e8cadeba4a429736dbdc17e3246b0154635bf216eb28bfcbc5c"},"schema_version":"1.0","source":{"id":"2501.07761","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07761","created_at":"2026-06-24T00:14:20Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07761v2","created_at":"2026-06-24T00:14:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07761","created_at":"2026-06-24T00:14:20Z"},{"alias_kind":"pith_short_12","alias_value":"STAOABRLMVOY","created_at":"2026-06-24T00:14:20Z"},{"alias_kind":"pith_short_16","alias_value":"STAOABRLMVOYMJ5O","created_at":"2026-06-24T00:14:20Z"},{"alias_kind":"pith_short_8","alias_value":"STAOABRL","created_at":"2026-06-24T00:14:20Z"}],"graph_snapshots":[{"event_id":"sha256:9558157e3de27c32fd3cfbc6d541a5b4095670f1f1130f16132ed52f8e192c45","target":"graph","created_at":"2026-06-24T00:14:20Z","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/2501.07761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Increasingly, recommender systems are tasked with improving users' long-term satisfaction. In this context, we study a content exploration task, which we formalize as a bandit problem with delayed rewards. There is an apparent trade-off in choosing the learning signal: waiting for the full reward to become available might take several weeks, slowing the rate of learning, whereas using short-term proxy rewards reflects the actual long-term goal only imperfectly. First, we develop a predictive model of delayed rewards that incorporates all information obtained to date. Rewards as well as shorter","authors_text":"Daniel Russo, Kamil Ciosek, Kelly W. Zhang, Lucas Maystre, Thomas Baldwin-McDonald","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T00:28:26Z","title":"Impatient Bandits: Optimizing for the Long-Term Without Delay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07761","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":"sha256:86df646cddf8830cde9f602dbad6a5f1f9f0299882cd9d311e585b2cc136d56e","target":"record","created_at":"2026-06-24T00:14:20Z","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":"e1c249c287792ae70393029d8a7f780cc1ffff4658e35817bb2544d98a56e697","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-14T00:28:26Z","title_canon_sha256":"6e7a22fa07a37e8cadeba4a429736dbdc17e3246b0154635bf216eb28bfcbc5c"},"schema_version":"1.0","source":{"id":"2501.07761","kind":"arxiv","version":2}},"canonical_sha256":"94c0e0062b655d8627ae0acfd23ce8cfaa43b9e21facae8f26d6072896aff4d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94c0e0062b655d8627ae0acfd23ce8cfaa43b9e21facae8f26d6072896aff4d1","first_computed_at":"2026-06-24T00:14:20.309024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T00:14:20.309024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n7L9v4um9g0vt9ZtDKVhDt8wqdwAXO95plWhcZYKjG6A13kNiAk31OYaCZgbuwgNnPWjEiU8GFlxpMjwXzteBw==","signature_status":"signed_v1","signed_at":"2026-06-24T00:14:20.309554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07761","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86df646cddf8830cde9f602dbad6a5f1f9f0299882cd9d311e585b2cc136d56e","sha256:9558157e3de27c32fd3cfbc6d541a5b4095670f1f1130f16132ed52f8e192c45"],"state_sha256":"71a0d06f8dc79a2da8f2a5673e29d8e5edf61c6fa94dbce7c9a407843aaf2d3f"}