{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LR65CSEVYKUPPD5EPL2Y5FGXCA","short_pith_number":"pith:LR65CSEV","schema_version":"1.0","canonical_sha256":"5c7dd14895c2a8f78fa47af58e94d71016f63f3d6890bab6ccc3d8999ac133b6","source":{"kind":"arxiv","id":"2405.10596","version":3},"attestation_state":"computed","paper":{"title":"CELA: Cost-Efficient Language Model Alignment for CTR Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Defu Lian, Qi Liu, Ruiming Tang, Weiwen Liu, Xiangyang Li, Xiaolong Chen, Xingmei Wang, Xu Huang, Yasheng Wang, Yichao Wang, Zhenhua Dong","submitted_at":"2024-05-17T07:43:25Z","abstract_excerpt":"Click-Through Rate (CTR) prediction holds a paramount position in recommender systems. The prevailing ID-based paradigm underperforms in cold-start scenarios due to the skewed distribution of feature frequency. Additionally, the utilization of a single modality fails to exploit the knowledge contained within textual features. Recent efforts have sought to mitigate these challenges by integrating Pre-trained Language Models (PLMs). They design hard prompts to structure raw features into text for each interaction and then apply PLMs for text processing. With external knowledge and reasoning capa"},"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":"2405.10596","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-17T07:43:25Z","cross_cats_sorted":[],"title_canon_sha256":"42e7b5c08f1a7d984d84c1c536afe4e2dffa8299adff7832cc93a7975b4423d2","abstract_canon_sha256":"042dfa7ebe87e037d0c417b9f478013d625807c967107b32dc7a0aebcc46ec72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:57.351497Z","signature_b64":"IPbxv2Df+Jqtj/MBNrihKYzqKPxpaHZw+m/ZzHa8Ip6UjLqrFrg6C+0+86OHdy7Dy3Qxn6ZZ+c+LBxJYWv+ZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c7dd14895c2a8f78fa47af58e94d71016f63f3d6890bab6ccc3d8999ac133b6","last_reissued_at":"2026-07-05T09:40:57.350978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:57.350978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CELA: Cost-Efficient Language Model Alignment for CTR Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Defu Lian, Qi Liu, Ruiming Tang, Weiwen Liu, Xiangyang Li, Xiaolong Chen, Xingmei Wang, Xu Huang, Yasheng Wang, Yichao Wang, Zhenhua Dong","submitted_at":"2024-05-17T07:43:25Z","abstract_excerpt":"Click-Through Rate (CTR) prediction holds a paramount position in recommender systems. The prevailing ID-based paradigm underperforms in cold-start scenarios due to the skewed distribution of feature frequency. Additionally, the utilization of a single modality fails to exploit the knowledge contained within textual features. Recent efforts have sought to mitigate these challenges by integrating Pre-trained Language Models (PLMs). They design hard prompts to structure raw features into text for each interaction and then apply PLMs for text processing. With external knowledge and reasoning capa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10596","kind":"arxiv","version":3},"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/2405.10596/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":"2405.10596","created_at":"2026-07-05T09:40:57.351047+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10596v3","created_at":"2026-07-05T09:40:57.351047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10596","created_at":"2026-07-05T09:40:57.351047+00:00"},{"alias_kind":"pith_short_12","alias_value":"LR65CSEVYKUP","created_at":"2026-07-05T09:40:57.351047+00:00"},{"alias_kind":"pith_short_16","alias_value":"LR65CSEVYKUPPD5E","created_at":"2026-07-05T09:40:57.351047+00:00"},{"alias_kind":"pith_short_8","alias_value":"LR65CSEV","created_at":"2026-07-05T09:40:57.351047+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.21986","citing_title":"SpecTran: Spectral-Aware Transformer-based Adapter for LLM-Enhanced Sequential Recommendation","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LR65CSEVYKUPPD5EPL2Y5FGXCA","json":"https://pith.science/pith/LR65CSEVYKUPPD5EPL2Y5FGXCA.json","graph_json":"https://pith.science/api/pith-number/LR65CSEVYKUPPD5EPL2Y5FGXCA/graph.json","events_json":"https://pith.science/api/pith-number/LR65CSEVYKUPPD5EPL2Y5FGXCA/events.json","paper":"https://pith.science/paper/LR65CSEV"},"agent_actions":{"view_html":"https://pith.science/pith/LR65CSEVYKUPPD5EPL2Y5FGXCA","download_json":"https://pith.science/pith/LR65CSEVYKUPPD5EPL2Y5FGXCA.json","view_paper":"https://pith.science/paper/LR65CSEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10596&json=true","fetch_graph":"https://pith.science/api/pith-number/LR65CSEVYKUPPD5EPL2Y5FGXCA/graph.json","fetch_events":"https://pith.science/api/pith-number/LR65CSEVYKUPPD5EPL2Y5FGXCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LR65CSEVYKUPPD5EPL2Y5FGXCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LR65CSEVYKUPPD5EPL2Y5FGXCA/action/storage_attestation","attest_author":"https://pith.science/pith/LR65CSEVYKUPPD5EPL2Y5FGXCA/action/author_attestation","sign_citation":"https://pith.science/pith/LR65CSEVYKUPPD5EPL2Y5FGXCA/action/citation_signature","submit_replication":"https://pith.science/pith/LR65CSEVYKUPPD5EPL2Y5FGXCA/action/replication_record"}},"created_at":"2026-07-05T09:40:57.351047+00:00","updated_at":"2026-07-05T09:40:57.351047+00:00"}