{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T7AZ7AXOJGQL2FOJB3DZ6BTUEC","short_pith_number":"pith:T7AZ7AXO","schema_version":"1.0","canonical_sha256":"9fc19f82ee49a0bd15c90ec79f067420a09f556513cecda6e778daa68bcd5f0e","source":{"kind":"arxiv","id":"2508.09730","version":1},"attestation_state":"computed","paper":{"title":"Generative Modeling with Multi-Instance Reward Learning for E-commerce Creative Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changping Peng, Ching Law, Dingyi Zeng, Jingping Shao, Lu Wang, Ming Pang, Qiaolei Gu, Yu Li, Zhangang Lin","submitted_at":"2025-08-13T11:53:41Z","abstract_excerpt":"In e-commerce advertising, selecting the most compelling combination of creative elements -- such as titles, images, and highlights -- is critical for capturing user attention and driving conversions. However, existing methods often evaluate creative components individually, failing to navigate the exponentially large search space of possible combinations. To address this challenge, we propose a novel framework named GenCO that integrates generative modeling with multi-instance reward learning. Our unified two-stage architecture first employs a generative model to efficiently produce a diverse"},"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":"2508.09730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T11:53:41Z","cross_cats_sorted":[],"title_canon_sha256":"98a89d4cc9a77f466b2b09b3b14781eaec3c7b5883d94eaf0c297761e1cc2c4b","abstract_canon_sha256":"3b4a791dc7308eb2713bb639521f547570480584faca5319e5c5576f13da25bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:20.850544Z","signature_b64":"M1ILUgplrHU6/L+dG1qDB2wwhk7cFIvpb9pCUJL+HsMBKt+hpt9r1gBhjf3RIYDrnkwmvhTpV35vdEMUn2ARCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fc19f82ee49a0bd15c90ec79f067420a09f556513cecda6e778daa68bcd5f0e","last_reissued_at":"2026-07-05T11:53:20.850038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:20.850038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Modeling with Multi-Instance Reward Learning for E-commerce Creative Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changping Peng, Ching Law, Dingyi Zeng, Jingping Shao, Lu Wang, Ming Pang, Qiaolei Gu, Yu Li, Zhangang Lin","submitted_at":"2025-08-13T11:53:41Z","abstract_excerpt":"In e-commerce advertising, selecting the most compelling combination of creative elements -- such as titles, images, and highlights -- is critical for capturing user attention and driving conversions. However, existing methods often evaluate creative components individually, failing to navigate the exponentially large search space of possible combinations. To address this challenge, we propose a novel framework named GenCO that integrates generative modeling with multi-instance reward learning. Our unified two-stage architecture first employs a generative model to efficiently produce a diverse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09730","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/2508.09730/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":"2508.09730","created_at":"2026-07-05T11:53:20.850095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09730v1","created_at":"2026-07-05T11:53:20.850095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09730","created_at":"2026-07-05T11:53:20.850095+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7AZ7AXOJGQL","created_at":"2026-07-05T11:53:20.850095+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7AZ7AXOJGQL2FOJ","created_at":"2026-07-05T11:53:20.850095+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7AZ7AXO","created_at":"2026-07-05T11:53:20.850095+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/T7AZ7AXOJGQL2FOJB3DZ6BTUEC","json":"https://pith.science/pith/T7AZ7AXOJGQL2FOJB3DZ6BTUEC.json","graph_json":"https://pith.science/api/pith-number/T7AZ7AXOJGQL2FOJB3DZ6BTUEC/graph.json","events_json":"https://pith.science/api/pith-number/T7AZ7AXOJGQL2FOJB3DZ6BTUEC/events.json","paper":"https://pith.science/paper/T7AZ7AXO"},"agent_actions":{"view_html":"https://pith.science/pith/T7AZ7AXOJGQL2FOJB3DZ6BTUEC","download_json":"https://pith.science/pith/T7AZ7AXOJGQL2FOJB3DZ6BTUEC.json","view_paper":"https://pith.science/paper/T7AZ7AXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09730&json=true","fetch_graph":"https://pith.science/api/pith-number/T7AZ7AXOJGQL2FOJB3DZ6BTUEC/graph.json","fetch_events":"https://pith.science/api/pith-number/T7AZ7AXOJGQL2FOJB3DZ6BTUEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7AZ7AXOJGQL2FOJB3DZ6BTUEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7AZ7AXOJGQL2FOJB3DZ6BTUEC/action/storage_attestation","attest_author":"https://pith.science/pith/T7AZ7AXOJGQL2FOJB3DZ6BTUEC/action/author_attestation","sign_citation":"https://pith.science/pith/T7AZ7AXOJGQL2FOJB3DZ6BTUEC/action/citation_signature","submit_replication":"https://pith.science/pith/T7AZ7AXOJGQL2FOJB3DZ6BTUEC/action/replication_record"}},"created_at":"2026-07-05T11:53:20.850095+00:00","updated_at":"2026-07-05T11:53:20.850095+00:00"}