{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:T7AUYZFP4JSEYCM2SHFIBZOKZE","short_pith_number":"pith:T7AUYZFP","schema_version":"1.0","canonical_sha256":"9fc14c64afe2644c099a91ca80e5cac915f6c4e6095eacc82ac669872ca72089","source":{"kind":"arxiv","id":"2112.11136","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Bo Zheng, Hongbo Deng, Kailun Wu, Lejian Ren, Shiming Xiang, Shuguang Han, Weijie Bian, Zhangming Chan","submitted_at":"2021-12-21T12:13:07Z","abstract_excerpt":"Exploration-Exploitation (E{\\&}E) algorithms are commonly adopted to deal with the feedback-loop issue in large-scale online recommender systems. Most of existing studies believe that high uncertainty can be a good indicator of potential reward, and thus primarily focus on the estimation of model uncertainty. We argue that such an approach overlooks the subsequent effect of exploration on model training. From the perspective of online learning, the adoption of an exploration strategy would also affect the collecting of training data, which further influences model learning. To understand the i"},"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":"2112.11136","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-12-21T12:13:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ea18690c18cad787a85454b8dc0d8067bb060deeb35ed36ffb3c45bbc5ed6c9b","abstract_canon_sha256":"3e81a4e0d2900a05e99728356c4333c3de27a57ef2d59d4c4da6730dd887cb35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:09.905672Z","signature_b64":"vdWrIHj2C7NGYwbKGuoUVihfwmYDz27CVVsYlUsneMw+6MmOkTqc88Vrc5NzRsm+XP50a64+UDO1ueZ8n8hoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fc14c64afe2644c099a91ca80e5cac915f6c4e6095eacc82ac669872ca72089","last_reissued_at":"2026-07-05T04:27:09.905151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:09.905151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Bo Zheng, Hongbo Deng, Kailun Wu, Lejian Ren, Shiming Xiang, Shuguang Han, Weijie Bian, Zhangming Chan","submitted_at":"2021-12-21T12:13:07Z","abstract_excerpt":"Exploration-Exploitation (E{\\&}E) algorithms are commonly adopted to deal with the feedback-loop issue in large-scale online recommender systems. Most of existing studies believe that high uncertainty can be a good indicator of potential reward, and thus primarily focus on the estimation of model uncertainty. We argue that such an approach overlooks the subsequent effect of exploration on model training. From the perspective of online learning, the adoption of an exploration strategy would also affect the collecting of training data, which further influences model learning. To understand the i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11136","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/2112.11136/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":"2112.11136","created_at":"2026-07-05T04:27:09.905220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11136v2","created_at":"2026-07-05T04:27:09.905220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11136","created_at":"2026-07-05T04:27:09.905220+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7AUYZFP4JSE","created_at":"2026-07-05T04:27:09.905220+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7AUYZFP4JSEYCM2","created_at":"2026-07-05T04:27:09.905220+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7AUYZFP","created_at":"2026-07-05T04:27:09.905220+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/T7AUYZFP4JSEYCM2SHFIBZOKZE","json":"https://pith.science/pith/T7AUYZFP4JSEYCM2SHFIBZOKZE.json","graph_json":"https://pith.science/api/pith-number/T7AUYZFP4JSEYCM2SHFIBZOKZE/graph.json","events_json":"https://pith.science/api/pith-number/T7AUYZFP4JSEYCM2SHFIBZOKZE/events.json","paper":"https://pith.science/paper/T7AUYZFP"},"agent_actions":{"view_html":"https://pith.science/pith/T7AUYZFP4JSEYCM2SHFIBZOKZE","download_json":"https://pith.science/pith/T7AUYZFP4JSEYCM2SHFIBZOKZE.json","view_paper":"https://pith.science/paper/T7AUYZFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11136&json=true","fetch_graph":"https://pith.science/api/pith-number/T7AUYZFP4JSEYCM2SHFIBZOKZE/graph.json","fetch_events":"https://pith.science/api/pith-number/T7AUYZFP4JSEYCM2SHFIBZOKZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7AUYZFP4JSEYCM2SHFIBZOKZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7AUYZFP4JSEYCM2SHFIBZOKZE/action/storage_attestation","attest_author":"https://pith.science/pith/T7AUYZFP4JSEYCM2SHFIBZOKZE/action/author_attestation","sign_citation":"https://pith.science/pith/T7AUYZFP4JSEYCM2SHFIBZOKZE/action/citation_signature","submit_replication":"https://pith.science/pith/T7AUYZFP4JSEYCM2SHFIBZOKZE/action/replication_record"}},"created_at":"2026-07-05T04:27:09.905220+00:00","updated_at":"2026-07-05T04:27:09.905220+00:00"}