{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2SCI5CNPBWBX3TI3TPD57CKTBB","short_pith_number":"pith:2SCI5CNP","schema_version":"1.0","canonical_sha256":"d4848e89af0d837dcd1b9bc7df8953087c54e037008c33605ae420420088b226","source":{"kind":"arxiv","id":"2312.08727","version":1},"attestation_state":"computed","paper":{"title":"Calibration-compatible Listwise Distillation of Privileged Features for CTR Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bo Zheng, Guoxian Yu, Jian Xu, Shuguang Han, Xiang-Rong Sheng, Xiaoqiang Gui, Yueyao Cheng, Yunfeng Zhao, Yuning Jiang","submitted_at":"2023-12-14T08:15:02Z","abstract_excerpt":"In machine learning systems, privileged features refer to the features that are available during offline training but inaccessible for online serving. Previous studies have recognized the importance of privileged features and explored ways to tackle online-offline discrepancies. A typical practice is privileged features distillation (PFD): train a teacher model using all features (including privileged ones) and then distill the knowledge from the teacher model using a student model (excluding the privileged features), which is then employed for online serving. In practice, the pointwise cross-"},"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":"2312.08727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-12-14T08:15:02Z","cross_cats_sorted":[],"title_canon_sha256":"403a2cb039af7f39f92e456e6eade80da8831783d7f135db9c496b6b951a45cc","abstract_canon_sha256":"fdbb5a9697ea3eb58ebb7ec642b5734a352b0ba9a772324b8b46bac06f010482"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:08.662549Z","signature_b64":"iCVOdyfFJi+VoXhj2FGNO12ta5o1NZIvr66BAA1MfEodq8xEjgocOy/dPsyYxtcuaPQwyO+6MCdz4dwzJpc8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4848e89af0d837dcd1b9bc7df8953087c54e037008c33605ae420420088b226","last_reissued_at":"2026-07-05T07:24:08.662141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:08.662141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibration-compatible Listwise Distillation of Privileged Features for CTR Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bo Zheng, Guoxian Yu, Jian Xu, Shuguang Han, Xiang-Rong Sheng, Xiaoqiang Gui, Yueyao Cheng, Yunfeng Zhao, Yuning Jiang","submitted_at":"2023-12-14T08:15:02Z","abstract_excerpt":"In machine learning systems, privileged features refer to the features that are available during offline training but inaccessible for online serving. Previous studies have recognized the importance of privileged features and explored ways to tackle online-offline discrepancies. A typical practice is privileged features distillation (PFD): train a teacher model using all features (including privileged ones) and then distill the knowledge from the teacher model using a student model (excluding the privileged features), which is then employed for online serving. In practice, the pointwise cross-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08727","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/2312.08727/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":"2312.08727","created_at":"2026-07-05T07:24:08.662199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08727v1","created_at":"2026-07-05T07:24:08.662199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08727","created_at":"2026-07-05T07:24:08.662199+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SCI5CNPBWBX","created_at":"2026-07-05T07:24:08.662199+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SCI5CNPBWBX3TI3","created_at":"2026-07-05T07:24:08.662199+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SCI5CNP","created_at":"2026-07-05T07:24:08.662199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10284","citing_title":"A Hybrid Cross-Stage Coordination Pre-ranking Model for Online Recommendation Systems","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2SCI5CNPBWBX3TI3TPD57CKTBB","json":"https://pith.science/pith/2SCI5CNPBWBX3TI3TPD57CKTBB.json","graph_json":"https://pith.science/api/pith-number/2SCI5CNPBWBX3TI3TPD57CKTBB/graph.json","events_json":"https://pith.science/api/pith-number/2SCI5CNPBWBX3TI3TPD57CKTBB/events.json","paper":"https://pith.science/paper/2SCI5CNP"},"agent_actions":{"view_html":"https://pith.science/pith/2SCI5CNPBWBX3TI3TPD57CKTBB","download_json":"https://pith.science/pith/2SCI5CNPBWBX3TI3TPD57CKTBB.json","view_paper":"https://pith.science/paper/2SCI5CNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08727&json=true","fetch_graph":"https://pith.science/api/pith-number/2SCI5CNPBWBX3TI3TPD57CKTBB/graph.json","fetch_events":"https://pith.science/api/pith-number/2SCI5CNPBWBX3TI3TPD57CKTBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SCI5CNPBWBX3TI3TPD57CKTBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SCI5CNPBWBX3TI3TPD57CKTBB/action/storage_attestation","attest_author":"https://pith.science/pith/2SCI5CNPBWBX3TI3TPD57CKTBB/action/author_attestation","sign_citation":"https://pith.science/pith/2SCI5CNPBWBX3TI3TPD57CKTBB/action/citation_signature","submit_replication":"https://pith.science/pith/2SCI5CNPBWBX3TI3TPD57CKTBB/action/replication_record"}},"created_at":"2026-07-05T07:24:08.662199+00:00","updated_at":"2026-07-05T07:24:08.662199+00:00"}