{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5Z3UG3BAXAA5UX5AXUXWZNVBOB","short_pith_number":"pith:5Z3UG3BA","schema_version":"1.0","canonical_sha256":"ee77436c20b801da5fa0bd2f6cb6a1705f765cd1ccc41f91d416f092924c328a","source":{"kind":"arxiv","id":"2205.08943","version":1},"attestation_state":"computed","paper":{"title":"CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Liang Wang, Penghui Wei, Shaoguo Liu, Xuanhua Yang","submitted_at":"2022-05-18T14:17:04Z","abstract_excerpt":"This paper focuses on automatically generating the text of an ad, and the goal is that the generated text can capture user interest for achieving higher click-through rate (CTR). We propose CREATER, a CTR-driven advertising text generation approach, to generate ad texts based on high-quality user reviews. To incorporate CTR objective, our model learns from online A/B test data with contrastive learning, which encourages the model to generate ad texts that obtain higher CTR. To alleviate the low-resource issue, we design a customized self-supervised objective reducing the gap between pre-traini"},"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":"2205.08943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T14:17:04Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"085207ed453d1f4d00b63cb323a0bae8c4e58be6b81270508dd89b2cbf271b6e","abstract_canon_sha256":"e460577b5601f1fcf49bfedb4cfc4065d82f64be6260027e6016e014d19b5e16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:31.171761Z","signature_b64":"LwCEfgamxNg+ADihXkYYNsy6g/NrqyBMNd78qFpxGvNDJ4bE9aYHqd+8Dt1Vde/IZr6m20ZT74PUj+7U6JWDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee77436c20b801da5fa0bd2f6cb6a1705f765cd1ccc41f91d416f092924c328a","last_reissued_at":"2026-07-05T04:24:31.171346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:31.171346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Liang Wang, Penghui Wei, Shaoguo Liu, Xuanhua Yang","submitted_at":"2022-05-18T14:17:04Z","abstract_excerpt":"This paper focuses on automatically generating the text of an ad, and the goal is that the generated text can capture user interest for achieving higher click-through rate (CTR). We propose CREATER, a CTR-driven advertising text generation approach, to generate ad texts based on high-quality user reviews. To incorporate CTR objective, our model learns from online A/B test data with contrastive learning, which encourages the model to generate ad texts that obtain higher CTR. To alleviate the low-resource issue, we design a customized self-supervised objective reducing the gap between pre-traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08943","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/2205.08943/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":"2205.08943","created_at":"2026-07-05T04:24:31.171405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.08943v1","created_at":"2026-07-05T04:24:31.171405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08943","created_at":"2026-07-05T04:24:31.171405+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Z3UG3BAXAA5","created_at":"2026-07-05T04:24:31.171405+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Z3UG3BAXAA5UX5A","created_at":"2026-07-05T04:24:31.171405+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Z3UG3BA","created_at":"2026-07-05T04:24:31.171405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12138","citing_title":"Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Z3UG3BAXAA5UX5AXUXWZNVBOB","json":"https://pith.science/pith/5Z3UG3BAXAA5UX5AXUXWZNVBOB.json","graph_json":"https://pith.science/api/pith-number/5Z3UG3BAXAA5UX5AXUXWZNVBOB/graph.json","events_json":"https://pith.science/api/pith-number/5Z3UG3BAXAA5UX5AXUXWZNVBOB/events.json","paper":"https://pith.science/paper/5Z3UG3BA"},"agent_actions":{"view_html":"https://pith.science/pith/5Z3UG3BAXAA5UX5AXUXWZNVBOB","download_json":"https://pith.science/pith/5Z3UG3BAXAA5UX5AXUXWZNVBOB.json","view_paper":"https://pith.science/paper/5Z3UG3BA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.08943&json=true","fetch_graph":"https://pith.science/api/pith-number/5Z3UG3BAXAA5UX5AXUXWZNVBOB/graph.json","fetch_events":"https://pith.science/api/pith-number/5Z3UG3BAXAA5UX5AXUXWZNVBOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Z3UG3BAXAA5UX5AXUXWZNVBOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Z3UG3BAXAA5UX5AXUXWZNVBOB/action/storage_attestation","attest_author":"https://pith.science/pith/5Z3UG3BAXAA5UX5AXUXWZNVBOB/action/author_attestation","sign_citation":"https://pith.science/pith/5Z3UG3BAXAA5UX5AXUXWZNVBOB/action/citation_signature","submit_replication":"https://pith.science/pith/5Z3UG3BAXAA5UX5AXUXWZNVBOB/action/replication_record"}},"created_at":"2026-07-05T04:24:31.171405+00:00","updated_at":"2026-07-05T04:24:31.171405+00:00"}