{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D2QJBZRCKJJNTV53HOMGZ6JX6Q","short_pith_number":"pith:D2QJBZRC","schema_version":"1.0","canonical_sha256":"1ea090e6225252d9d7bb3b986cf937f41d291f185ae3ad9e096bcd7a11800ae0","source":{"kind":"arxiv","id":"2411.16122","version":2},"attestation_state":"computed","paper":{"title":"From Collapse to Stability: A Knowledge-Driven Ensemble Framework for Scaling Up Click-Through Rate Prediction Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Guangming Cui, Honghao Li, Lei Sang, Yiwen Zhang, Yi Zhang","submitted_at":"2024-11-25T06:14:20Z","abstract_excerpt":"Click-through rate (CTR) prediction plays a crucial role in modern recommender systems. While many existing methods utilize ensemble networks to improve CTR model performance, they typically restrict the ensemble to only two or three sub-networks. Whether increasing the number of sub-networks consistently enhances CTR model performance to align with scaling laws remains unclear. In this paper, we investigate larger ensemble networks and find three inherent limitations in commonly used ensemble methods: (1) performance degradation as the number of sub-networks increases; (2) sharp declines and "},"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":"2411.16122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-11-25T06:14:20Z","cross_cats_sorted":[],"title_canon_sha256":"57373ad027a3096b2697ddc0d8f87b243874c7a4a717c4b52b813d97b12fdb92","abstract_canon_sha256":"7f8bd02d520581006cfb12a46a68540015e40292e9be4aaa4045d330ab6dc84a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:09.340981Z","signature_b64":"c/hWFi1nIj/YbYLMd6bTnQrGjByVGM/S9huvNvap5tggJNUlGcRqPabz5/g9O8DIzGOZhBh63ckUOJN9fZmlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ea090e6225252d9d7bb3b986cf937f41d291f185ae3ad9e096bcd7a11800ae0","last_reissued_at":"2026-07-05T11:24:09.340471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:09.340471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Collapse to Stability: A Knowledge-Driven Ensemble Framework for Scaling Up Click-Through Rate Prediction Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Guangming Cui, Honghao Li, Lei Sang, Yiwen Zhang, Yi Zhang","submitted_at":"2024-11-25T06:14:20Z","abstract_excerpt":"Click-through rate (CTR) prediction plays a crucial role in modern recommender systems. While many existing methods utilize ensemble networks to improve CTR model performance, they typically restrict the ensemble to only two or three sub-networks. Whether increasing the number of sub-networks consistently enhances CTR model performance to align with scaling laws remains unclear. In this paper, we investigate larger ensemble networks and find three inherent limitations in commonly used ensemble methods: (1) performance degradation as the number of sub-networks increases; (2) sharp declines and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16122","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/2411.16122/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":"2411.16122","created_at":"2026-07-05T11:24:09.340536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16122v2","created_at":"2026-07-05T11:24:09.340536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16122","created_at":"2026-07-05T11:24:09.340536+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2QJBZRCKJJN","created_at":"2026-07-05T11:24:09.340536+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2QJBZRCKJJNTV53","created_at":"2026-07-05T11:24:09.340536+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2QJBZRC","created_at":"2026-07-05T11:24:09.340536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17999","citing_title":"Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2QJBZRCKJJNTV53HOMGZ6JX6Q","json":"https://pith.science/pith/D2QJBZRCKJJNTV53HOMGZ6JX6Q.json","graph_json":"https://pith.science/api/pith-number/D2QJBZRCKJJNTV53HOMGZ6JX6Q/graph.json","events_json":"https://pith.science/api/pith-number/D2QJBZRCKJJNTV53HOMGZ6JX6Q/events.json","paper":"https://pith.science/paper/D2QJBZRC"},"agent_actions":{"view_html":"https://pith.science/pith/D2QJBZRCKJJNTV53HOMGZ6JX6Q","download_json":"https://pith.science/pith/D2QJBZRCKJJNTV53HOMGZ6JX6Q.json","view_paper":"https://pith.science/paper/D2QJBZRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16122&json=true","fetch_graph":"https://pith.science/api/pith-number/D2QJBZRCKJJNTV53HOMGZ6JX6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/D2QJBZRCKJJNTV53HOMGZ6JX6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2QJBZRCKJJNTV53HOMGZ6JX6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2QJBZRCKJJNTV53HOMGZ6JX6Q/action/storage_attestation","attest_author":"https://pith.science/pith/D2QJBZRCKJJNTV53HOMGZ6JX6Q/action/author_attestation","sign_citation":"https://pith.science/pith/D2QJBZRCKJJNTV53HOMGZ6JX6Q/action/citation_signature","submit_replication":"https://pith.science/pith/D2QJBZRCKJJNTV53HOMGZ6JX6Q/action/replication_record"}},"created_at":"2026-07-05T11:24:09.340536+00:00","updated_at":"2026-07-05T11:24:09.340536+00:00"}