{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HZZWE7NKDP2K4XJM6JR6IRF5XI","short_pith_number":"pith:HZZWE7NK","schema_version":"1.0","canonical_sha256":"3e73627daa1bf4ae5d2cf263e444bdba0f23eb08fc16225ead31d4bdefbff21a","source":{"kind":"arxiv","id":"2509.04126","version":2},"attestation_state":"computed","paper":{"title":"MEPG:Multi-Expert Planning and Generation for Compositionally-Rich Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lin Liu, Yuan Zhao","submitted_at":"2025-09-04T11:44:28Z","abstract_excerpt":"Text-to-image diffusion models have achieved remarkable image quality, but they still struggle with complex, multiele ment prompts, and limited stylistic diversity. To address these limitations, we propose a Multi-Expert Planning and Gen eration Framework (MEPG) that synergistically integrates position- and style-aware large language models (LLMs) with spatial-semantic expert modules. The framework comprises two core components: (1) a Position-Style-Aware (PSA) module that utilizes a supervised fine-tuned LLM to decom pose input prompts into precise spatial coordinates and style encoded semant"},"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":"2509.04126","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T11:44:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fe5bbb575d9d85476c9337c5e5fbe82fc365e1136e4234f4b76be18144c31b29","abstract_canon_sha256":"8ffab4cd2d30d9f521126f87108cea479db7708e76a72dbc96297aa9c44ecdd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:20.471882Z","signature_b64":"n5zcXnRhrCABm6WOmW9GTt2t0E+j009iv3C5+9UjT9B8CN0DJnytxOPX1bsgFmy4/93NTGzPMpC6N4hmCEshBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e73627daa1bf4ae5d2cf263e444bdba0f23eb08fc16225ead31d4bdefbff21a","last_reissued_at":"2026-07-05T12:11:20.471356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:20.471356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MEPG:Multi-Expert Planning and Generation for Compositionally-Rich Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lin Liu, Yuan Zhao","submitted_at":"2025-09-04T11:44:28Z","abstract_excerpt":"Text-to-image diffusion models have achieved remarkable image quality, but they still struggle with complex, multiele ment prompts, and limited stylistic diversity. To address these limitations, we propose a Multi-Expert Planning and Gen eration Framework (MEPG) that synergistically integrates position- and style-aware large language models (LLMs) with spatial-semantic expert modules. The framework comprises two core components: (1) a Position-Style-Aware (PSA) module that utilizes a supervised fine-tuned LLM to decom pose input prompts into precise spatial coordinates and style encoded semant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04126","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/2509.04126/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":"2509.04126","created_at":"2026-07-05T12:11:20.471418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04126v2","created_at":"2026-07-05T12:11:20.471418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04126","created_at":"2026-07-05T12:11:20.471418+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZZWE7NKDP2K","created_at":"2026-07-05T12:11:20.471418+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZZWE7NKDP2K4XJM","created_at":"2026-07-05T12:11:20.471418+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZZWE7NK","created_at":"2026-07-05T12:11:20.471418+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/HZZWE7NKDP2K4XJM6JR6IRF5XI","json":"https://pith.science/pith/HZZWE7NKDP2K4XJM6JR6IRF5XI.json","graph_json":"https://pith.science/api/pith-number/HZZWE7NKDP2K4XJM6JR6IRF5XI/graph.json","events_json":"https://pith.science/api/pith-number/HZZWE7NKDP2K4XJM6JR6IRF5XI/events.json","paper":"https://pith.science/paper/HZZWE7NK"},"agent_actions":{"view_html":"https://pith.science/pith/HZZWE7NKDP2K4XJM6JR6IRF5XI","download_json":"https://pith.science/pith/HZZWE7NKDP2K4XJM6JR6IRF5XI.json","view_paper":"https://pith.science/paper/HZZWE7NK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04126&json=true","fetch_graph":"https://pith.science/api/pith-number/HZZWE7NKDP2K4XJM6JR6IRF5XI/graph.json","fetch_events":"https://pith.science/api/pith-number/HZZWE7NKDP2K4XJM6JR6IRF5XI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZZWE7NKDP2K4XJM6JR6IRF5XI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZZWE7NKDP2K4XJM6JR6IRF5XI/action/storage_attestation","attest_author":"https://pith.science/pith/HZZWE7NKDP2K4XJM6JR6IRF5XI/action/author_attestation","sign_citation":"https://pith.science/pith/HZZWE7NKDP2K4XJM6JR6IRF5XI/action/citation_signature","submit_replication":"https://pith.science/pith/HZZWE7NKDP2K4XJM6JR6IRF5XI/action/replication_record"}},"created_at":"2026-07-05T12:11:20.471418+00:00","updated_at":"2026-07-05T12:11:20.471418+00:00"}