{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3MJFCYE45EJMLZUL33JMXSO33R","short_pith_number":"pith:3MJFCYE4","schema_version":"1.0","canonical_sha256":"db1251609ce912c5e68bded2cbc9dbdc53ca901821fed29e7b28c3a6f34ce54b","source":{"kind":"arxiv","id":"2606.00954","version":1},"attestation_state":"computed","paper":{"title":"COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengyu Lin, Jia Wei, Teng Zhou, Xiaoyu Zhang, Xinlong Zhang, Yongchuan Tang","submitted_at":"2026-05-31T02:10:34Z","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"},"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":"2606.00954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T02:10:34Z","cross_cats_sorted":[],"title_canon_sha256":"de2762981a16ae24a5d969f5c768ff13cd5c8c1d3f7c195ece009aa0d514eb5c","abstract_canon_sha256":"479a7a5c28625eec870c033a7fb29f88d0bcf984e2cad3cd68e7948e0b2bea00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:10.345081Z","signature_b64":"sJpNskDyx7XQPYW867SuR6dW7pAcZx8kxhPq2YAWE8zCMZXb5qiOFp4ysevLQYGG5E8zP872r/0jYfMz0gLECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db1251609ce912c5e68bded2cbc9dbdc53ca901821fed29e7b28c3a6f34ce54b","last_reissued_at":"2026-06-02T01:04:10.344461Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:10.344461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COLLAR: Cascaded Object-Level Latent Refinement for High-Fidelity Conditional Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengyu Lin, Jia Wei, Teng Zhou, Xiaoyu Zhang, Xinlong Zhang, Yongchuan Tang","submitted_at":"2026-05-31T02:10:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00954","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/2606.00954/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":"2606.00954","created_at":"2026-06-02T01:04:10.344556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00954v1","created_at":"2026-06-02T01:04:10.344556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00954","created_at":"2026-06-02T01:04:10.344556+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MJFCYE45EJM","created_at":"2026-06-02T01:04:10.344556+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MJFCYE45EJMLZUL","created_at":"2026-06-02T01:04:10.344556+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MJFCYE4","created_at":"2026-06-02T01:04:10.344556+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/3MJFCYE45EJMLZUL33JMXSO33R","json":"https://pith.science/pith/3MJFCYE45EJMLZUL33JMXSO33R.json","graph_json":"https://pith.science/api/pith-number/3MJFCYE45EJMLZUL33JMXSO33R/graph.json","events_json":"https://pith.science/api/pith-number/3MJFCYE45EJMLZUL33JMXSO33R/events.json","paper":"https://pith.science/paper/3MJFCYE4"},"agent_actions":{"view_html":"https://pith.science/pith/3MJFCYE45EJMLZUL33JMXSO33R","download_json":"https://pith.science/pith/3MJFCYE45EJMLZUL33JMXSO33R.json","view_paper":"https://pith.science/paper/3MJFCYE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00954&json=true","fetch_graph":"https://pith.science/api/pith-number/3MJFCYE45EJMLZUL33JMXSO33R/graph.json","fetch_events":"https://pith.science/api/pith-number/3MJFCYE45EJMLZUL33JMXSO33R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MJFCYE45EJMLZUL33JMXSO33R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MJFCYE45EJMLZUL33JMXSO33R/action/storage_attestation","attest_author":"https://pith.science/pith/3MJFCYE45EJMLZUL33JMXSO33R/action/author_attestation","sign_citation":"https://pith.science/pith/3MJFCYE45EJMLZUL33JMXSO33R/action/citation_signature","submit_replication":"https://pith.science/pith/3MJFCYE45EJMLZUL33JMXSO33R/action/replication_record"}},"created_at":"2026-06-02T01:04:10.344556+00:00","updated_at":"2026-06-02T01:04:10.344556+00:00"}