{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YJQPKQYCKBOFFAGSVF6O2ESQW2","short_pith_number":"pith:YJQPKQYC","schema_version":"1.0","canonical_sha256":"c260f54302505c5280d2a97ced1250b6b3bb1ac888c2400ae0bbaf7bfce1fc8e","source":{"kind":"arxiv","id":"2010.11060","version":4},"attestation_state":"computed","paper":{"title":"A Critical Study on Data Leakage in Recommender System Offline Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aixin Sun, Chenliang Li, Jie Zhang, Yitong Ji","submitted_at":"2020-10-21T15:09:20Z","abstract_excerpt":"Recommender models are hard to evaluate, particularly under offline setting. In this paper, we provide a comprehensive and critical analysis of the data leakage issue in recommender system offline evaluation. Data leakage is caused by not observing global timeline in evaluating recommenders, e.g., train/test data split does not follow global timeline. As a result, a model learns from the user-item interactions that are not expected to be available at prediction time. We first show the temporal dynamics of user-item interactions along global timeline, then explain why data leakage exists for co"},"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":"2010.11060","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-10-21T15:09:20Z","cross_cats_sorted":[],"title_canon_sha256":"60b67510e11873de1e23c95e4a6895dfa4814dfa66eff2770a643e8588778af2","abstract_canon_sha256":"1a3f1116f97a8a79fe272566ad5e21382f9c805e608dae9271487893748edc64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:26.740782Z","signature_b64":"P+Ts4JDV0FvBmO8i3zkjGP1TSU0YPRB2P2TTQ+MC0negAZtGwMxfYKoB6Ebymr2nSl9O05TJXEjRmjdifDilDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c260f54302505c5280d2a97ced1250b6b3bb1ac888c2400ae0bbaf7bfce1fc8e","last_reissued_at":"2026-07-05T06:37:26.740301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:26.740301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Critical Study on Data Leakage in Recommender System Offline Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Aixin Sun, Chenliang Li, Jie Zhang, Yitong Ji","submitted_at":"2020-10-21T15:09:20Z","abstract_excerpt":"Recommender models are hard to evaluate, particularly under offline setting. In this paper, we provide a comprehensive and critical analysis of the data leakage issue in recommender system offline evaluation. Data leakage is caused by not observing global timeline in evaluating recommenders, e.g., train/test data split does not follow global timeline. As a result, a model learns from the user-item interactions that are not expected to be available at prediction time. We first show the temporal dynamics of user-item interactions along global timeline, then explain why data leakage exists for co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11060","kind":"arxiv","version":4},"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/2010.11060/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":"2010.11060","created_at":"2026-07-05T06:37:26.740374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.11060v4","created_at":"2026-07-05T06:37:26.740374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11060","created_at":"2026-07-05T06:37:26.740374+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJQPKQYCKBOF","created_at":"2026-07-05T06:37:26.740374+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJQPKQYCKBOFFAGS","created_at":"2026-07-05T06:37:26.740374+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJQPKQYC","created_at":"2026-07-05T06:37:26.740374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJQPKQYCKBOFFAGSVF6O2ESQW2","json":"https://pith.science/pith/YJQPKQYCKBOFFAGSVF6O2ESQW2.json","graph_json":"https://pith.science/api/pith-number/YJQPKQYCKBOFFAGSVF6O2ESQW2/graph.json","events_json":"https://pith.science/api/pith-number/YJQPKQYCKBOFFAGSVF6O2ESQW2/events.json","paper":"https://pith.science/paper/YJQPKQYC"},"agent_actions":{"view_html":"https://pith.science/pith/YJQPKQYCKBOFFAGSVF6O2ESQW2","download_json":"https://pith.science/pith/YJQPKQYCKBOFFAGSVF6O2ESQW2.json","view_paper":"https://pith.science/paper/YJQPKQYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.11060&json=true","fetch_graph":"https://pith.science/api/pith-number/YJQPKQYCKBOFFAGSVF6O2ESQW2/graph.json","fetch_events":"https://pith.science/api/pith-number/YJQPKQYCKBOFFAGSVF6O2ESQW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJQPKQYCKBOFFAGSVF6O2ESQW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJQPKQYCKBOFFAGSVF6O2ESQW2/action/storage_attestation","attest_author":"https://pith.science/pith/YJQPKQYCKBOFFAGSVF6O2ESQW2/action/author_attestation","sign_citation":"https://pith.science/pith/YJQPKQYCKBOFFAGSVF6O2ESQW2/action/citation_signature","submit_replication":"https://pith.science/pith/YJQPKQYCKBOFFAGSVF6O2ESQW2/action/replication_record"}},"created_at":"2026-07-05T06:37:26.740374+00:00","updated_at":"2026-07-05T06:37:26.740374+00:00"}