{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WSVP6R6B4B4KNGLTZPBRJFNMAK","short_pith_number":"pith:WSVP6R6B","schema_version":"1.0","canonical_sha256":"b4aaff47c1e078a69973cbc31495ac02bf7d367202840fd9636bb5d280113594","source":{"kind":"arxiv","id":"2608.06878","version":1},"attestation_state":"computed","paper":{"title":"ControlRef: Efficient Layout-Guided Multi-Instance Generation via Anchored 4D-RoPE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyuan Liang, Jinshuai Cheng, Kunquan Zhang, Liziyue Fang, Runmin Dong, Weitao Wan, Xinying Chen, Yizhuo Niu, Yudong Zhang, Yunkai Yang","submitted_at":"2026-08-07T07:05:25Z","abstract_excerpt":"Layout-guided multi-instance generation is essential for controllable image synthesis in Multi-Modal Diffusion Transformers (MM-DiTs). However, integrating this capability into unified architectures remains challenging. Prior frameworks rely on redundant full-resolution canvas padding and Shifted-RoPE to manage multiple reference images. This mechanism drastically inflates computational overhead for sparse layouts and disrupts critical low-frequency RoPE features, creating a severe spatial-frequency compromise that blurs absolute spatial correspondence. To overcome these limitations, we propos"},"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":"2608.06878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T07:05:25Z","cross_cats_sorted":[],"title_canon_sha256":"db6c7386407ca4a4a6278cdb822dc68fc87693aaf1201549ffa632cd245272ef","abstract_canon_sha256":"03784d74d1a480c4e16870f9e2959db693f170baf4282650b3d50470704c3f92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:12:23.286092Z","signature_b64":"DYNMVI/fDMoXqJKnzbbJD+Vgr+HsQRbwejOSqjoVMEThQoD/pmVhWWYtGEtQetxZn1rO4o1QE12muLTixkueBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4aaff47c1e078a69973cbc31495ac02bf7d367202840fd9636bb5d280113594","last_reissued_at":"2026-08-10T01:12:23.283733Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:12:23.283733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ControlRef: Efficient Layout-Guided Multi-Instance Generation via Anchored 4D-RoPE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyuan Liang, Jinshuai Cheng, Kunquan Zhang, Liziyue Fang, Runmin Dong, Weitao Wan, Xinying Chen, Yizhuo Niu, Yudong Zhang, Yunkai Yang","submitted_at":"2026-08-07T07:05:25Z","abstract_excerpt":"Layout-guided multi-instance generation is essential for controllable image synthesis in Multi-Modal Diffusion Transformers (MM-DiTs). However, integrating this capability into unified architectures remains challenging. Prior frameworks rely on redundant full-resolution canvas padding and Shifted-RoPE to manage multiple reference images. This mechanism drastically inflates computational overhead for sparse layouts and disrupts critical low-frequency RoPE features, creating a severe spatial-frequency compromise that blurs absolute spatial correspondence. To overcome these limitations, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06878","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/2608.06878/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":"2608.06878","created_at":"2026-08-10T01:12:23.284682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06878v1","created_at":"2026-08-10T01:12:23.284682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06878","created_at":"2026-08-10T01:12:23.284682+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSVP6R6B4B4K","created_at":"2026-08-10T01:12:23.284682+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSVP6R6B4B4KNGLT","created_at":"2026-08-10T01:12:23.284682+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSVP6R6B","created_at":"2026-08-10T01:12:23.284682+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/WSVP6R6B4B4KNGLTZPBRJFNMAK","json":"https://pith.science/pith/WSVP6R6B4B4KNGLTZPBRJFNMAK.json","graph_json":"https://pith.science/api/pith-number/WSVP6R6B4B4KNGLTZPBRJFNMAK/graph.json","events_json":"https://pith.science/api/pith-number/WSVP6R6B4B4KNGLTZPBRJFNMAK/events.json","paper":"https://pith.science/paper/WSVP6R6B"},"agent_actions":{"view_html":"https://pith.science/pith/WSVP6R6B4B4KNGLTZPBRJFNMAK","download_json":"https://pith.science/pith/WSVP6R6B4B4KNGLTZPBRJFNMAK.json","view_paper":"https://pith.science/paper/WSVP6R6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06878&json=true","fetch_graph":"https://pith.science/api/pith-number/WSVP6R6B4B4KNGLTZPBRJFNMAK/graph.json","fetch_events":"https://pith.science/api/pith-number/WSVP6R6B4B4KNGLTZPBRJFNMAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSVP6R6B4B4KNGLTZPBRJFNMAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSVP6R6B4B4KNGLTZPBRJFNMAK/action/storage_attestation","attest_author":"https://pith.science/pith/WSVP6R6B4B4KNGLTZPBRJFNMAK/action/author_attestation","sign_citation":"https://pith.science/pith/WSVP6R6B4B4KNGLTZPBRJFNMAK/action/citation_signature","submit_replication":"https://pith.science/pith/WSVP6R6B4B4KNGLTZPBRJFNMAK/action/replication_record"}},"created_at":"2026-08-10T01:12:23.284682+00:00","updated_at":"2026-08-10T01:12:23.284682+00:00"}