{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:E3FR3IZEGQSIMTX3OY5VELRVSA","short_pith_number":"pith:E3FR3IZE","schema_version":"1.0","canonical_sha256":"26cb1da3243424864efb763b522e359025004aae28e946151e49dda110c912b7","source":{"kind":"arxiv","id":"1907.05171","version":2},"attestation_state":"computed","paper":{"title":"Privileged Features Distillation at Taobao Recommendations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Changhua Pei, Chen Xu, Fei Sun, Hanxiao Sun, Jian Wu, Jinyang Gao, Junfeng Ge, Quan Li, Wenwu Ou, Xiaoyong Yang","submitted_at":"2019-07-11T13:05:51Z","abstract_excerpt":"Features play an important role in the prediction tasks of e-commerce recommendations. To guarantee the consistency of off-line training and on-line serving, we usually utilize the same features that are both available. However, the consistency in turn neglects some discriminative features. For example, when estimating the conversion rate (CVR), i.e., the probability that a user would purchase the item if she clicked it, features like dwell time on the item detailed page are informative. However, CVR prediction should be conducted for on-line ranking before the click happens. Thus we cannot ge"},"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":"1907.05171","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-07-11T13:05:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"180364f18b91714852767054c20e1f973c7c4d18724c93a8210d93eef727d476","abstract_canon_sha256":"cec4488fa0ccf792c0049d2c2c6b80ad6aeaca7654313ff10b8e10c5859131dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:55.012256Z","signature_b64":"lCvziQ8XspgrzAP9AD3kQeskqUGL60iVYgE1qf93mhB1yC5r33DyTf1Dkag2wgii+e6EfUV+xaoRGePwy3arDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26cb1da3243424864efb763b522e359025004aae28e946151e49dda110c912b7","last_reissued_at":"2026-07-05T00:43:55.011821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:55.011821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privileged Features Distillation at Taobao Recommendations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Changhua Pei, Chen Xu, Fei Sun, Hanxiao Sun, Jian Wu, Jinyang Gao, Junfeng Ge, Quan Li, Wenwu Ou, Xiaoyong Yang","submitted_at":"2019-07-11T13:05:51Z","abstract_excerpt":"Features play an important role in the prediction tasks of e-commerce recommendations. To guarantee the consistency of off-line training and on-line serving, we usually utilize the same features that are both available. However, the consistency in turn neglects some discriminative features. For example, when estimating the conversion rate (CVR), i.e., the probability that a user would purchase the item if she clicked it, features like dwell time on the item detailed page are informative. However, CVR prediction should be conducted for on-line ranking before the click happens. Thus we cannot ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05171","kind":"arxiv","version":2},"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/1907.05171/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":"1907.05171","created_at":"2026-07-05T00:43:55.011883+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05171v2","created_at":"2026-07-05T00:43:55.011883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05171","created_at":"2026-07-05T00:43:55.011883+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3FR3IZEGQSI","created_at":"2026-07-05T00:43:55.011883+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3FR3IZEGQSIMTX3","created_at":"2026-07-05T00:43:55.011883+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3FR3IZE","created_at":"2026-07-05T00:43:55.011883+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.27055","citing_title":"Learning from the Future: Privileged Self-Distillation for Sequential Recommendation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E3FR3IZEGQSIMTX3OY5VELRVSA","json":"https://pith.science/pith/E3FR3IZEGQSIMTX3OY5VELRVSA.json","graph_json":"https://pith.science/api/pith-number/E3FR3IZEGQSIMTX3OY5VELRVSA/graph.json","events_json":"https://pith.science/api/pith-number/E3FR3IZEGQSIMTX3OY5VELRVSA/events.json","paper":"https://pith.science/paper/E3FR3IZE"},"agent_actions":{"view_html":"https://pith.science/pith/E3FR3IZEGQSIMTX3OY5VELRVSA","download_json":"https://pith.science/pith/E3FR3IZEGQSIMTX3OY5VELRVSA.json","view_paper":"https://pith.science/paper/E3FR3IZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05171&json=true","fetch_graph":"https://pith.science/api/pith-number/E3FR3IZEGQSIMTX3OY5VELRVSA/graph.json","fetch_events":"https://pith.science/api/pith-number/E3FR3IZEGQSIMTX3OY5VELRVSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3FR3IZEGQSIMTX3OY5VELRVSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3FR3IZEGQSIMTX3OY5VELRVSA/action/storage_attestation","attest_author":"https://pith.science/pith/E3FR3IZEGQSIMTX3OY5VELRVSA/action/author_attestation","sign_citation":"https://pith.science/pith/E3FR3IZEGQSIMTX3OY5VELRVSA/action/citation_signature","submit_replication":"https://pith.science/pith/E3FR3IZEGQSIMTX3OY5VELRVSA/action/replication_record"}},"created_at":"2026-07-05T00:43:55.011883+00:00","updated_at":"2026-07-05T00:43:55.011883+00:00"}