{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5CMNZAZEOUAUT2EVBG3AAPJINZ","short_pith_number":"pith:5CMNZAZE","schema_version":"1.0","canonical_sha256":"e898dc8324750149e89509b6003d286e6c4a05063d1df2287ad9db9ab30c7d96","source":{"kind":"arxiv","id":"2508.18118","version":1},"attestation_state":"computed","paper":{"title":"HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Bingyue Peng, Junyi Chen, Lu Chi, Shiwei Ran, Siliang Xu, Zehuan Yuan","submitted_at":"2025-08-25T15:23:21Z","abstract_excerpt":"AI-generated content technologies are widely used in content creation. However, current AIGC systems rely heavily on creators' inspiration, rarely generating truly user-personalized content. In real-world applications such as online advertising, a single product may have multiple selling points, with different users focusing on different features. This underscores the significant value of personalized, user-centric creative generation. Effective personalized content generation faces two main challenges: (1) accurately modeling user interests and integrating them into the content generation pro"},"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":"2508.18118","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-25T15:23:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"545dba8e17547ba95ced39e9a3eaf317205143b54e5c40f830e9a0343887a1b2","abstract_canon_sha256":"34254e480f6fa17d9b479a411244316646fa2ee9daa3fadbe8217cb81c8c9fc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:54.046966Z","signature_b64":"jA6YeronaHM3SOq7tcqtCVKRWMse5X12MdSpkuolkFG15QkGyXsSzrLKIdX7c12AfhHbHyHupYDEjiCXK3JLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e898dc8324750149e89509b6003d286e6c4a05063d1df2287ad9db9ab30c7d96","last_reissued_at":"2026-07-05T11:58:54.046455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:54.046455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Bingyue Peng, Junyi Chen, Lu Chi, Shiwei Ran, Siliang Xu, Zehuan Yuan","submitted_at":"2025-08-25T15:23:21Z","abstract_excerpt":"AI-generated content technologies are widely used in content creation. However, current AIGC systems rely heavily on creators' inspiration, rarely generating truly user-personalized content. In real-world applications such as online advertising, a single product may have multiple selling points, with different users focusing on different features. This underscores the significant value of personalized, user-centric creative generation. Effective personalized content generation faces two main challenges: (1) accurately modeling user interests and integrating them into the content generation pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18118","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/2508.18118/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":"2508.18118","created_at":"2026-07-05T11:58:54.046515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18118v1","created_at":"2026-07-05T11:58:54.046515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18118","created_at":"2026-07-05T11:58:54.046515+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CMNZAZEOUAU","created_at":"2026-07-05T11:58:54.046515+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CMNZAZEOUAUT2EV","created_at":"2026-07-05T11:58:54.046515+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CMNZAZE","created_at":"2026-07-05T11:58:54.046515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25496","citing_title":"Recommendation as Generation: Unifying Personalized Video Generation and Recommendation at Industrial Scale","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.10673","citing_title":"Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12138","citing_title":"Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CMNZAZEOUAUT2EVBG3AAPJINZ","json":"https://pith.science/pith/5CMNZAZEOUAUT2EVBG3AAPJINZ.json","graph_json":"https://pith.science/api/pith-number/5CMNZAZEOUAUT2EVBG3AAPJINZ/graph.json","events_json":"https://pith.science/api/pith-number/5CMNZAZEOUAUT2EVBG3AAPJINZ/events.json","paper":"https://pith.science/paper/5CMNZAZE"},"agent_actions":{"view_html":"https://pith.science/pith/5CMNZAZEOUAUT2EVBG3AAPJINZ","download_json":"https://pith.science/pith/5CMNZAZEOUAUT2EVBG3AAPJINZ.json","view_paper":"https://pith.science/paper/5CMNZAZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18118&json=true","fetch_graph":"https://pith.science/api/pith-number/5CMNZAZEOUAUT2EVBG3AAPJINZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5CMNZAZEOUAUT2EVBG3AAPJINZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CMNZAZEOUAUT2EVBG3AAPJINZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CMNZAZEOUAUT2EVBG3AAPJINZ/action/storage_attestation","attest_author":"https://pith.science/pith/5CMNZAZEOUAUT2EVBG3AAPJINZ/action/author_attestation","sign_citation":"https://pith.science/pith/5CMNZAZEOUAUT2EVBG3AAPJINZ/action/citation_signature","submit_replication":"https://pith.science/pith/5CMNZAZEOUAUT2EVBG3AAPJINZ/action/replication_record"}},"created_at":"2026-07-05T11:58:54.046515+00:00","updated_at":"2026-07-05T11:58:54.046515+00:00"}