{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GCT4H4I4C466U7FQF7U7SNHT3G","short_pith_number":"pith:GCT4H4I4","schema_version":"1.0","canonical_sha256":"30a7c3f11c173dea7cb02fe9f934f3d9aaa898feb9a474e5e92bc147019754f3","source":{"kind":"arxiv","id":"2407.12223","version":5},"attestation_state":"computed","paper":{"title":"Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengzhi Lin, Chuyuan Wang, Shuchang Liu, Yongqi Liu","submitted_at":"2024-07-17T00:25:35Z","abstract_excerpt":"Accurately predicting watch time is crucial for optimizing recommendations and user experience in short video platforms. However, existing methods that estimate a single average watch time often fail to capture the inherent uncertainty in user engagement patterns. In this paper, we propose Conditional Quantile Estimation (CQE) to model the entire conditional distribution of watch time. Using quantile regression, CQE characterizes the complex watch-time distribution for each user-video pair, providing a flexible and comprehensive approach to understanding user behavior. We further design multip"},"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":"2407.12223","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-17T00:25:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ce113ed611fb4021b0520abcff3547e1ec28026bcbada825e6853006bd73ceb8","abstract_canon_sha256":"dd9a5e939e5c4edb8b4c357b5096741e7253816c1b69df343aa6578d159e4741"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:38.539467Z","signature_b64":"+/MDgwomOBG4/FYRSeIweYVFFGMYQj5LFdKu6neB/5qKUFKoLEbyLqdD+wxz3iR1OnlMZfWwYYR1tPtImtdtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30a7c3f11c173dea7cb02fe9f934f3d9aaa898feb9a474e5e92bc147019754f3","last_reissued_at":"2026-07-05T11:04:38.538971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:38.538971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengzhi Lin, Chuyuan Wang, Shuchang Liu, Yongqi Liu","submitted_at":"2024-07-17T00:25:35Z","abstract_excerpt":"Accurately predicting watch time is crucial for optimizing recommendations and user experience in short video platforms. However, existing methods that estimate a single average watch time often fail to capture the inherent uncertainty in user engagement patterns. In this paper, we propose Conditional Quantile Estimation (CQE) to model the entire conditional distribution of watch time. Using quantile regression, CQE characterizes the complex watch-time distribution for each user-video pair, providing a flexible and comprehensive approach to understanding user behavior. We further design multip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12223","kind":"arxiv","version":5},"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/2407.12223/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":"2407.12223","created_at":"2026-07-05T11:04:38.539027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12223v5","created_at":"2026-07-05T11:04:38.539027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12223","created_at":"2026-07-05T11:04:38.539027+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCT4H4I4C466","created_at":"2026-07-05T11:04:38.539027+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCT4H4I4C466U7FQ","created_at":"2026-07-05T11:04:38.539027+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCT4H4I4","created_at":"2026-07-05T11:04:38.539027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08202","citing_title":"PIT-SUN: A Deployable Empirical Marginal Transform Framework with Expectation-Consistent Recovery for Regression in Recommender Systems","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25188","citing_title":"Efficient Analytic Uncertainty Quantification for Multi-Modal Regression","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17863","citing_title":"DADF: A Distribution-Aware Debiasing Framework for Watch-Time Regression in Recommender Systems","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21752","citing_title":"PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17863","citing_title":"DADF: A Distribution-Aware Debiasing Framework for Watch-Time Regression in Recommender Systems","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCT4H4I4C466U7FQF7U7SNHT3G","json":"https://pith.science/pith/GCT4H4I4C466U7FQF7U7SNHT3G.json","graph_json":"https://pith.science/api/pith-number/GCT4H4I4C466U7FQF7U7SNHT3G/graph.json","events_json":"https://pith.science/api/pith-number/GCT4H4I4C466U7FQF7U7SNHT3G/events.json","paper":"https://pith.science/paper/GCT4H4I4"},"agent_actions":{"view_html":"https://pith.science/pith/GCT4H4I4C466U7FQF7U7SNHT3G","download_json":"https://pith.science/pith/GCT4H4I4C466U7FQF7U7SNHT3G.json","view_paper":"https://pith.science/paper/GCT4H4I4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12223&json=true","fetch_graph":"https://pith.science/api/pith-number/GCT4H4I4C466U7FQF7U7SNHT3G/graph.json","fetch_events":"https://pith.science/api/pith-number/GCT4H4I4C466U7FQF7U7SNHT3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCT4H4I4C466U7FQF7U7SNHT3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCT4H4I4C466U7FQF7U7SNHT3G/action/storage_attestation","attest_author":"https://pith.science/pith/GCT4H4I4C466U7FQF7U7SNHT3G/action/author_attestation","sign_citation":"https://pith.science/pith/GCT4H4I4C466U7FQF7U7SNHT3G/action/citation_signature","submit_replication":"https://pith.science/pith/GCT4H4I4C466U7FQF7U7SNHT3G/action/replication_record"}},"created_at":"2026-07-05T11:04:38.539027+00:00","updated_at":"2026-07-05T11:04:38.539027+00:00"}