{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BSIJECJAN6IHQCPYZO2WVYN2O6","short_pith_number":"pith:BSIJECJA","schema_version":"1.0","canonical_sha256":"0c909209206f907809f8cbb56ae1ba77acfb5ec758e1c566f19414bf95872206","source":{"kind":"arxiv","id":"2508.14500","version":2},"attestation_state":"computed","paper":{"title":"DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jinxin Hu, Moyu Zhang, Yujun Jin, Yun Chen, Yu Zhang","submitted_at":"2025-08-20T07:42:21Z","abstract_excerpt":"Recent advances in generative models have inspired the field of recommender systems to explore generative approaches, but most existing research focuses on sequence generation, a paradigm ill-suited for click-through rate (CTR) prediction. CTR models critically depend on a large number of cross-features between the target item and the user to estimate the probability of clicking on the item, and discarding these cross-features will significantly impair model performance. Therefore, to harness the ability of generative models to understand data distributions and thereby alleviate the constraint"},"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":"2508.14500","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-20T07:42:21Z","cross_cats_sorted":[],"title_canon_sha256":"d4ddcb2b949d87c62772d95a24619ffd3836aea64a8d042641f6c1d32fe706fe","abstract_canon_sha256":"bbceb6213755a43d8e7b523e37947c1b0e3ebd64209d96b9aba6832cf7d24e1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:09.022685Z","signature_b64":"lLkKbiPP+DT9/0BhbybwVoL8zUQ2PrPTfTApNGBQ2Wwh0bIPMtmYkECcPBv31wI67z0azDI4OivG6y2JL160AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c909209206f907809f8cbb56ae1ba77acfb5ec758e1c566f19414bf95872206","last_reissued_at":"2026-07-05T12:00:09.022179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:09.022179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DGenCTR: Towards a Universal Generative Paradigm for Click-Through Rate Prediction via Discrete Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jinxin Hu, Moyu Zhang, Yujun Jin, Yun Chen, Yu Zhang","submitted_at":"2025-08-20T07:42:21Z","abstract_excerpt":"Recent advances in generative models have inspired the field of recommender systems to explore generative approaches, but most existing research focuses on sequence generation, a paradigm ill-suited for click-through rate (CTR) prediction. CTR models critically depend on a large number of cross-features between the target item and the user to estimate the probability of clicking on the item, and discarding these cross-features will significantly impair model performance. Therefore, to harness the ability of generative models to understand data distributions and thereby alleviate the constraint"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14500","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/2508.14500/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":"2508.14500","created_at":"2026-07-05T12:00:09.022241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14500v2","created_at":"2026-07-05T12:00:09.022241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14500","created_at":"2026-07-05T12:00:09.022241+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSIJECJAN6IH","created_at":"2026-07-05T12:00:09.022241+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSIJECJAN6IHQCPY","created_at":"2026-07-05T12:00:09.022241+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSIJECJA","created_at":"2026-07-05T12:00:09.022241+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04944","citing_title":"Dual-Stream MLP is All You Need for CTR Prediction","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24989","citing_title":"Selective Test-Time Compute Scaling for Click-Through Rate Prediction via Uncertainty-Triggered Feature Path Exploration","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24986","citing_title":"Self-Balancing Gradient Allocation for Heterogeneity-Aware Feature Generation in Click-Through Rate Prediction","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSIJECJAN6IHQCPYZO2WVYN2O6","json":"https://pith.science/pith/BSIJECJAN6IHQCPYZO2WVYN2O6.json","graph_json":"https://pith.science/api/pith-number/BSIJECJAN6IHQCPYZO2WVYN2O6/graph.json","events_json":"https://pith.science/api/pith-number/BSIJECJAN6IHQCPYZO2WVYN2O6/events.json","paper":"https://pith.science/paper/BSIJECJA"},"agent_actions":{"view_html":"https://pith.science/pith/BSIJECJAN6IHQCPYZO2WVYN2O6","download_json":"https://pith.science/pith/BSIJECJAN6IHQCPYZO2WVYN2O6.json","view_paper":"https://pith.science/paper/BSIJECJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14500&json=true","fetch_graph":"https://pith.science/api/pith-number/BSIJECJAN6IHQCPYZO2WVYN2O6/graph.json","fetch_events":"https://pith.science/api/pith-number/BSIJECJAN6IHQCPYZO2WVYN2O6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSIJECJAN6IHQCPYZO2WVYN2O6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSIJECJAN6IHQCPYZO2WVYN2O6/action/storage_attestation","attest_author":"https://pith.science/pith/BSIJECJAN6IHQCPYZO2WVYN2O6/action/author_attestation","sign_citation":"https://pith.science/pith/BSIJECJAN6IHQCPYZO2WVYN2O6/action/citation_signature","submit_replication":"https://pith.science/pith/BSIJECJAN6IHQCPYZO2WVYN2O6/action/replication_record"}},"created_at":"2026-07-05T12:00:09.022241+00:00","updated_at":"2026-07-05T12:00:09.022241+00:00"}