{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CIFM656TM3AYTMXNHU2ZA7X6LA","short_pith_number":"pith:CIFM656T","schema_version":"1.0","canonical_sha256":"120acf77d366c189b2ed3d35907efe58008331c56232d16afee223aacaee114f","source":{"kind":"arxiv","id":"2209.08642","version":1},"attestation_state":"computed","paper":{"title":"Offline Evaluation of Reward-Optimizing Recommender Systems: The Case of Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Amine Benhalloum, Benjamin Heymann, David Rohde, Flavian Vasile, Imad Aouali, Martin Bompaire, Olivier Jeunen, Otmane Sakhi","submitted_at":"2022-09-18T20:03:32Z","abstract_excerpt":"Both in academic and industry-based research, online evaluation methods are seen as the golden standard for interactive applications like recommendation systems. Naturally, the reason for this is that we can directly measure utility metrics that rely on interventions, being the recommendations that are being shown to users. Nevertheless, online evaluation methods are costly for a number of reasons, and a clear need remains for reliable offline evaluation procedures. In industry, offline metrics are often used as a first-line evaluation to generate promising candidate models to evaluate online."},"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":"2209.08642","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-09-18T20:03:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6c3cc3cfae08764a4f7f0fcc2983690a2877b491e710d48157777ad3c96da60e","abstract_canon_sha256":"d627d6c477538bdee3e503cc5a6efadb0679ba7c7fbdfdd7694a1a264f12e10a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:43.803489Z","signature_b64":"Wfn1yXtIfX4u92yEi4sA/YNLNl25abClj2KK1tcLJWJ55/fAv8bzG4vCKry9/e1isY8W7P5X/TScondfpP2nAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"120acf77d366c189b2ed3d35907efe58008331c56232d16afee223aacaee114f","last_reissued_at":"2026-07-05T04:58:43.802984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:43.802984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Evaluation of Reward-Optimizing Recommender Systems: The Case of Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Amine Benhalloum, Benjamin Heymann, David Rohde, Flavian Vasile, Imad Aouali, Martin Bompaire, Olivier Jeunen, Otmane Sakhi","submitted_at":"2022-09-18T20:03:32Z","abstract_excerpt":"Both in academic and industry-based research, online evaluation methods are seen as the golden standard for interactive applications like recommendation systems. Naturally, the reason for this is that we can directly measure utility metrics that rely on interventions, being the recommendations that are being shown to users. Nevertheless, online evaluation methods are costly for a number of reasons, and a clear need remains for reliable offline evaluation procedures. In industry, offline metrics are often used as a first-line evaluation to generate promising candidate models to evaluate online."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08642","kind":"arxiv","version":1},"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/2209.08642/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":"2209.08642","created_at":"2026-07-05T04:58:43.803050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08642v1","created_at":"2026-07-05T04:58:43.803050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08642","created_at":"2026-07-05T04:58:43.803050+00:00"},{"alias_kind":"pith_short_12","alias_value":"CIFM656TM3AY","created_at":"2026-07-05T04:58:43.803050+00:00"},{"alias_kind":"pith_short_16","alias_value":"CIFM656TM3AYTMXN","created_at":"2026-07-05T04:58:43.803050+00:00"},{"alias_kind":"pith_short_8","alias_value":"CIFM656T","created_at":"2026-07-05T04:58:43.803050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09566","citing_title":"Identifying Offline Metrics that Predict Online Impact: A Pragmatic Strategy for Real-World Recommender Systems","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CIFM656TM3AYTMXNHU2ZA7X6LA","json":"https://pith.science/pith/CIFM656TM3AYTMXNHU2ZA7X6LA.json","graph_json":"https://pith.science/api/pith-number/CIFM656TM3AYTMXNHU2ZA7X6LA/graph.json","events_json":"https://pith.science/api/pith-number/CIFM656TM3AYTMXNHU2ZA7X6LA/events.json","paper":"https://pith.science/paper/CIFM656T"},"agent_actions":{"view_html":"https://pith.science/pith/CIFM656TM3AYTMXNHU2ZA7X6LA","download_json":"https://pith.science/pith/CIFM656TM3AYTMXNHU2ZA7X6LA.json","view_paper":"https://pith.science/paper/CIFM656T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08642&json=true","fetch_graph":"https://pith.science/api/pith-number/CIFM656TM3AYTMXNHU2ZA7X6LA/graph.json","fetch_events":"https://pith.science/api/pith-number/CIFM656TM3AYTMXNHU2ZA7X6LA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CIFM656TM3AYTMXNHU2ZA7X6LA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CIFM656TM3AYTMXNHU2ZA7X6LA/action/storage_attestation","attest_author":"https://pith.science/pith/CIFM656TM3AYTMXNHU2ZA7X6LA/action/author_attestation","sign_citation":"https://pith.science/pith/CIFM656TM3AYTMXNHU2ZA7X6LA/action/citation_signature","submit_replication":"https://pith.science/pith/CIFM656TM3AYTMXNHU2ZA7X6LA/action/replication_record"}},"created_at":"2026-07-05T04:58:43.803050+00:00","updated_at":"2026-07-05T04:58:43.803050+00:00"}