{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7ZWN23BIDB2AYLZTDUYK53K3KF","short_pith_number":"pith:7ZWN23BI","schema_version":"1.0","canonical_sha256":"fe6cdd6c2818740c2f331d30aeed5b5179f17f073e724a42c5bd39f41def9d5d","source":{"kind":"arxiv","id":"2406.02884","version":3},"attestation_state":"computed","paper":{"title":"PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Wen Chen, Tao Yang, Yang Wu, Yingmin Luo, Ying Shan, Zhongang Qi","submitted_at":"2024-06-05T03:05:52Z","abstract_excerpt":"Layout generation is the keystone in achieving automated graphic design, requiring arranging the position and size of various multi-modal design elements in a visually pleasing and constraint-following manner. Previous approaches are either inefficient for large-scale applications or lack flexibility for varying design requirements. Our research introduces a unified framework for automated graphic layout generation, leveraging the multi-modal large language model (MLLM) to accommodate diverse design tasks. In contrast, our data-driven method employs structured text (JSON format) and visual ins"},"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":"2406.02884","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T03:05:52Z","cross_cats_sorted":[],"title_canon_sha256":"935cf5b89ae8276455c4379450b06aac9996934a61dd6016de654a6447e6b638","abstract_canon_sha256":"04c09f74918a3a96683ae4c655bcfa171cfbd067c5e6adf1c6b4a28df02f5fac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:17.880060Z","signature_b64":"wOVtVEdl44QkcZUx/yAPCn2nIwN9MYUUyxrE8p+yulqgwO36Y5lsRBihyve8eRq7pA8SGIMKI3vG8uiLWPOqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe6cdd6c2818740c2f331d30aeed5b5179f17f073e724a42c5bd39f41def9d5d","last_reissued_at":"2026-07-05T09:40:17.879520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:17.879520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Wen Chen, Tao Yang, Yang Wu, Yingmin Luo, Ying Shan, Zhongang Qi","submitted_at":"2024-06-05T03:05:52Z","abstract_excerpt":"Layout generation is the keystone in achieving automated graphic design, requiring arranging the position and size of various multi-modal design elements in a visually pleasing and constraint-following manner. Previous approaches are either inefficient for large-scale applications or lack flexibility for varying design requirements. Our research introduces a unified framework for automated graphic layout generation, leveraging the multi-modal large language model (MLLM) to accommodate diverse design tasks. In contrast, our data-driven method employs structured text (JSON format) and visual ins"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02884","kind":"arxiv","version":3},"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/2406.02884/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":"2406.02884","created_at":"2026-07-05T09:40:17.879593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02884v3","created_at":"2026-07-05T09:40:17.879593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02884","created_at":"2026-07-05T09:40:17.879593+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZWN23BIDB2A","created_at":"2026-07-05T09:40:17.879593+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZWN23BIDB2AYLZT","created_at":"2026-07-05T09:40:17.879593+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZWN23BI","created_at":"2026-07-05T09:40:17.879593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02915","citing_title":"Any2Poster: Any-Source Poster Generation Across Modalities and Domains","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27235","citing_title":"MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ZWN23BIDB2AYLZTDUYK53K3KF","json":"https://pith.science/pith/7ZWN23BIDB2AYLZTDUYK53K3KF.json","graph_json":"https://pith.science/api/pith-number/7ZWN23BIDB2AYLZTDUYK53K3KF/graph.json","events_json":"https://pith.science/api/pith-number/7ZWN23BIDB2AYLZTDUYK53K3KF/events.json","paper":"https://pith.science/paper/7ZWN23BI"},"agent_actions":{"view_html":"https://pith.science/pith/7ZWN23BIDB2AYLZTDUYK53K3KF","download_json":"https://pith.science/pith/7ZWN23BIDB2AYLZTDUYK53K3KF.json","view_paper":"https://pith.science/paper/7ZWN23BI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02884&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZWN23BIDB2AYLZTDUYK53K3KF/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZWN23BIDB2AYLZTDUYK53K3KF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZWN23BIDB2AYLZTDUYK53K3KF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZWN23BIDB2AYLZTDUYK53K3KF/action/storage_attestation","attest_author":"https://pith.science/pith/7ZWN23BIDB2AYLZTDUYK53K3KF/action/author_attestation","sign_citation":"https://pith.science/pith/7ZWN23BIDB2AYLZTDUYK53K3KF/action/citation_signature","submit_replication":"https://pith.science/pith/7ZWN23BIDB2AYLZTDUYK53K3KF/action/replication_record"}},"created_at":"2026-07-05T09:40:17.879593+00:00","updated_at":"2026-07-05T09:40:17.879593+00:00"}