{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UOXHIICWJTKENB7RRJLDKFXTJR","short_pith_number":"pith:UOXHIICW","schema_version":"1.0","canonical_sha256":"a3ae7420564cd44687f18a563516f34c6008d75a68c92bf474985379947308ed","source":{"kind":"arxiv","id":"2501.01097","version":3},"attestation_state":"computed","paper":{"title":"EliGen: Entity-Level Controlled Image Generation with Regional Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Zhang, Xingjun Wang, Yingda Chen, Yu Zhang, Zhongjie Duan","submitted_at":"2025-01-02T06:46:13Z","abstract_excerpt":"Recent advancements in diffusion models have significantly advanced text-to-image generation, yet global text prompts alone remain insufficient for achieving fine-grained control over individual entities within an image. To address this limitation, we present EliGen, a novel framework for Entity-level controlled image Generation. Firstly, we put forward regional attention, a mechanism for diffusion transformers that requires no additional parameters, seamlessly integrating entity prompts and arbitrary-shaped spatial masks. By contributing a high-quality dataset with fine-grained spatial and se"},"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":"2501.01097","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T06:46:13Z","cross_cats_sorted":[],"title_canon_sha256":"3e43722bb1a6dabc195b6e4806de98d3f38c7fdad474b2bcb4062fa37f6059b0","abstract_canon_sha256":"7bfc6b580b10ca39130f87708fc3c5b17b3058458d8abbbe6de0dc66c0281228"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:02.688864Z","signature_b64":"bKmx6+zcci/q/8pTbvt3EgBjD8r6ArrheDkvmnX3Oum+GD5gI/koUK3+Fuww78xJJGBrVJMTx4sQRwCZUpT7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3ae7420564cd44687f18a563516f34c6008d75a68c92bf474985379947308ed","last_reissued_at":"2026-07-05T10:07:02.688416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:02.688416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EliGen: Entity-Level Controlled Image Generation with Regional Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Zhang, Xingjun Wang, Yingda Chen, Yu Zhang, Zhongjie Duan","submitted_at":"2025-01-02T06:46:13Z","abstract_excerpt":"Recent advancements in diffusion models have significantly advanced text-to-image generation, yet global text prompts alone remain insufficient for achieving fine-grained control over individual entities within an image. To address this limitation, we present EliGen, a novel framework for Entity-level controlled image Generation. Firstly, we put forward regional attention, a mechanism for diffusion transformers that requires no additional parameters, seamlessly integrating entity prompts and arbitrary-shaped spatial masks. By contributing a high-quality dataset with fine-grained spatial and se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01097","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/2501.01097/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":"2501.01097","created_at":"2026-07-05T10:07:02.688480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01097v3","created_at":"2026-07-05T10:07:02.688480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01097","created_at":"2026-07-05T10:07:02.688480+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOXHIICWJTKE","created_at":"2026-07-05T10:07:02.688480+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOXHIICWJTKENB7R","created_at":"2026-07-05T10:07:02.688480+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOXHIICW","created_at":"2026-07-05T10:07:02.688480+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05031","citing_title":"MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06870","citing_title":"RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14062","citing_title":"OneHOI: Unifying Human-Object Interaction Generation and Editing","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04609","citing_title":"Advancing Aesthetic Image Generation via Composition Transfer","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UOXHIICWJTKENB7RRJLDKFXTJR","json":"https://pith.science/pith/UOXHIICWJTKENB7RRJLDKFXTJR.json","graph_json":"https://pith.science/api/pith-number/UOXHIICWJTKENB7RRJLDKFXTJR/graph.json","events_json":"https://pith.science/api/pith-number/UOXHIICWJTKENB7RRJLDKFXTJR/events.json","paper":"https://pith.science/paper/UOXHIICW"},"agent_actions":{"view_html":"https://pith.science/pith/UOXHIICWJTKENB7RRJLDKFXTJR","download_json":"https://pith.science/pith/UOXHIICWJTKENB7RRJLDKFXTJR.json","view_paper":"https://pith.science/paper/UOXHIICW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01097&json=true","fetch_graph":"https://pith.science/api/pith-number/UOXHIICWJTKENB7RRJLDKFXTJR/graph.json","fetch_events":"https://pith.science/api/pith-number/UOXHIICWJTKENB7RRJLDKFXTJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOXHIICWJTKENB7RRJLDKFXTJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOXHIICWJTKENB7RRJLDKFXTJR/action/storage_attestation","attest_author":"https://pith.science/pith/UOXHIICWJTKENB7RRJLDKFXTJR/action/author_attestation","sign_citation":"https://pith.science/pith/UOXHIICWJTKENB7RRJLDKFXTJR/action/citation_signature","submit_replication":"https://pith.science/pith/UOXHIICWJTKENB7RRJLDKFXTJR/action/replication_record"}},"created_at":"2026-07-05T10:07:02.688480+00:00","updated_at":"2026-07-05T10:07:02.688480+00:00"}