{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3MJFCYE45EJMLZUL33JMXSO33R","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"479a7a5c28625eec870c033a7fb29f88d0bcf984e2cad3cd68e7948e0b2bea00","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T02:10:34Z","title_canon_sha256":"de2762981a16ae24a5d969f5c768ff13cd5c8c1d3f7c195ece009aa0d514eb5c"},"schema_version":"1.0","source":{"id":"2606.00954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00954","created_at":"2026-06-02T01:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00954v1","created_at":"2026-06-02T01:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00954","created_at":"2026-06-02T01:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"3MJFCYE45EJM","created_at":"2026-06-02T01:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"3MJFCYE45EJMLZUL","created_at":"2026-06-02T01:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"3MJFCYE4","created_at":"2026-06-02T01:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:3e36313a224ad8c1b5ab4005520714694dd58b3a1cb68b5b7d65174e143a0109","target":"graph","created_at":"2026-06-02T01:04:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.00954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Achieving high-fidelity object-level control in Diffusion Transformers remains a significant challenge despite the introduction of structural priors like depth and Canny maps. Current object-level conditional generation methods frequently suffer from visual artifacts and struggle to maintain precise control over objects within small localized regions. To address these limitations, we propose Cascaded Object-Level Latent Refinement (COLLAR), a training-free framework that progressively optimizes object-level features via the Field-of-View (FoV) expansion. First, we propose the Cross-Scale Seman","authors_text":"Chengyu Lin, Jia Wei, Teng Zhou, Xiaoyu Zhang, Xinlong Zhang, Yongchuan Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T02:10:34Z","title":"COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00954","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e7045b075af9fdfec9a02f26366fa6d138aa522f86466d323fa067cd67634392","target":"record","created_at":"2026-06-02T01:04:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"479a7a5c28625eec870c033a7fb29f88d0bcf984e2cad3cd68e7948e0b2bea00","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T02:10:34Z","title_canon_sha256":"de2762981a16ae24a5d969f5c768ff13cd5c8c1d3f7c195ece009aa0d514eb5c"},"schema_version":"1.0","source":{"id":"2606.00954","kind":"arxiv","version":1}},"canonical_sha256":"db1251609ce912c5e68bded2cbc9dbdc53ca901821fed29e7b28c3a6f34ce54b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db1251609ce912c5e68bded2cbc9dbdc53ca901821fed29e7b28c3a6f34ce54b","first_computed_at":"2026-06-02T01:04:10.344461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:10.344461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sJpNskDyx7XQPYW867SuR6dW7pAcZx8kxhPq2YAWE8zCMZXb5qiOFp4ysevLQYGG5E8zP872r/0jYfMz0gLECg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:10.345081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7045b075af9fdfec9a02f26366fa6d138aa522f86466d323fa067cd67634392","sha256:3e36313a224ad8c1b5ab4005520714694dd58b3a1cb68b5b7d65174e143a0109"],"state_sha256":"5e99274f534861567f243383a172bfe4fe4c84b3a125d10d72fc19044c1f954c"}