{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KNNSX4SDTHKY47H7V2DZEO2CYH","short_pith_number":"pith:KNNSX4SD","schema_version":"1.0","canonical_sha256":"535b2bf24399d58e7cffae87923b42c1ffd1bb99846d401aecfbec97023da0b0","source":{"kind":"arxiv","id":"2608.12778","version":1},"attestation_state":"computed","paper":{"title":"DrEM: Dual-Side Robust Ensemble Ranking from Noisy User Preference Predictions in Video Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Canwei Huang, Chunjie Chen, Jun Zhang, Kaiqiao Zhan, Tiantian He, Weike Pan, Xiaoxiao Xu, Ziran Deng","submitted_at":"2026-08-13T03:36:09Z","abstract_excerpt":"Industrial video recommendation systems typically adopt a multi-stage architecture. At the ensemble ranking stage, multi-dimensional user preference predictions (pxtrs) from an upstream multi-task model are fused into a unified ranking score to reflect user satisfaction. Since users' true satisfaction is difficult to observe directly, ensemble ranking models commonly use pxtrs both as input features and as a source for constructing proxy preferences. However, as outputs of an upstream prediction model, pxtrs inevitably contain prediction noise, which propagates to downstream learning across tw"},"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":"2608.12778","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-08-13T03:36:09Z","cross_cats_sorted":[],"title_canon_sha256":"412b228b360ff0ae0941b7ff9010648c8af7853466a0e3920d4ca0cec28777e9","abstract_canon_sha256":"73796441ee4598cf0e3b4014dffad8a772646b4efa15258e7b98c8edcd4d309d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:47:50.672058Z","signature_b64":"TylKAQvXfpnUXGBQJApMC7laJuc6cFqDzhb6iME0N+L3CJHUnEnuIfK5HnmmEudphM3OgPO2cKMcW98oZXxMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"535b2bf24399d58e7cffae87923b42c1ffd1bb99846d401aecfbec97023da0b0","last_reissued_at":"2026-08-14T00:47:50.664236Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:47:50.664236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DrEM: Dual-Side Robust Ensemble Ranking from Noisy User Preference Predictions in Video Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Canwei Huang, Chunjie Chen, Jun Zhang, Kaiqiao Zhan, Tiantian He, Weike Pan, Xiaoxiao Xu, Ziran Deng","submitted_at":"2026-08-13T03:36:09Z","abstract_excerpt":"Industrial video recommendation systems typically adopt a multi-stage architecture. At the ensemble ranking stage, multi-dimensional user preference predictions (pxtrs) from an upstream multi-task model are fused into a unified ranking score to reflect user satisfaction. Since users' true satisfaction is difficult to observe directly, ensemble ranking models commonly use pxtrs both as input features and as a source for constructing proxy preferences. However, as outputs of an upstream prediction model, pxtrs inevitably contain prediction noise, which propagates to downstream learning across tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12778","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/2608.12778/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":"2608.12778","created_at":"2026-08-14T00:47:50.668375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12778v1","created_at":"2026-08-14T00:47:50.668375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12778","created_at":"2026-08-14T00:47:50.668375+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNNSX4SDTHKY","created_at":"2026-08-14T00:47:50.668375+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNNSX4SDTHKY47H7","created_at":"2026-08-14T00:47:50.668375+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNNSX4SD","created_at":"2026-08-14T00:47:50.668375+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/KNNSX4SDTHKY47H7V2DZEO2CYH","json":"https://pith.science/pith/KNNSX4SDTHKY47H7V2DZEO2CYH.json","graph_json":"https://pith.science/api/pith-number/KNNSX4SDTHKY47H7V2DZEO2CYH/graph.json","events_json":"https://pith.science/api/pith-number/KNNSX4SDTHKY47H7V2DZEO2CYH/events.json","paper":"https://pith.science/paper/KNNSX4SD"},"agent_actions":{"view_html":"https://pith.science/pith/KNNSX4SDTHKY47H7V2DZEO2CYH","download_json":"https://pith.science/pith/KNNSX4SDTHKY47H7V2DZEO2CYH.json","view_paper":"https://pith.science/paper/KNNSX4SD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12778&json=true","fetch_graph":"https://pith.science/api/pith-number/KNNSX4SDTHKY47H7V2DZEO2CYH/graph.json","fetch_events":"https://pith.science/api/pith-number/KNNSX4SDTHKY47H7V2DZEO2CYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNNSX4SDTHKY47H7V2DZEO2CYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNNSX4SDTHKY47H7V2DZEO2CYH/action/storage_attestation","attest_author":"https://pith.science/pith/KNNSX4SDTHKY47H7V2DZEO2CYH/action/author_attestation","sign_citation":"https://pith.science/pith/KNNSX4SDTHKY47H7V2DZEO2CYH/action/citation_signature","submit_replication":"https://pith.science/pith/KNNSX4SDTHKY47H7V2DZEO2CYH/action/replication_record"}},"created_at":"2026-08-14T00:47:50.668375+00:00","updated_at":"2026-08-14T00:47:50.668375+00:00"}