{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GUUTGKIHHCSG7VX2BYZVH3HK4Y","short_pith_number":"pith:GUUTGKIH","schema_version":"1.0","canonical_sha256":"352933290738a46fd6fa0e3353eceae616ca4f70a6f3656a16693147a0e6d527","source":{"kind":"arxiv","id":"2606.30332","version":1},"attestation_state":"computed","paper":{"title":"UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Dongxu Yue, Fan Wang, Hao Luo, Qin Guo, Weixuan Jin, Xiao Fu","submitted_at":"2026-06-29T14:13:27Z","abstract_excerpt":"Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions. In this work, we introduce UniGP, a framework built upon MMDiT, which unifies controllable generation and dense prediction through simple joint training, without the need for complex task-specific designs or losses, while preserving the backbone's versatil"},"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":"2606.30332","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T14:13:27Z","cross_cats_sorted":[],"title_canon_sha256":"bd503526bc8c3940d50971bd51046f9282e023f2ebdf7081229fb19c65584b9f","abstract_canon_sha256":"d15267735a46898df512bef8899e3f4dae069e7d40ec089a3c0432330ec65bf5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:10.746762Z","signature_b64":"fnhlKXr7ryrF47Zq/Wwx7k6cjy+LhBMD+nPEPwHUnGUHQe8gCt3CXfPfSNZoa7LLOfhLA6RQdIRdk/gBOx/gCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"352933290738a46fd6fa0e3353eceae616ca4f70a6f3656a16693147a0e6d527","last_reissued_at":"2026-06-30T02:18:10.745952Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:10.745952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Dongxu Yue, Fan Wang, Hao Luo, Qin Guo, Weixuan Jin, Xiao Fu","submitted_at":"2026-06-29T14:13:27Z","abstract_excerpt":"Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions. In this work, we introduce UniGP, a framework built upon MMDiT, which unifies controllable generation and dense prediction through simple joint training, without the need for complex task-specific designs or losses, while preserving the backbone's versatil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30332","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/2606.30332/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":"2606.30332","created_at":"2026-06-30T02:18:10.746053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30332v1","created_at":"2026-06-30T02:18:10.746053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30332","created_at":"2026-06-30T02:18:10.746053+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUUTGKIHHCSG","created_at":"2026-06-30T02:18:10.746053+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUUTGKIHHCSG7VX2","created_at":"2026-06-30T02:18:10.746053+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUUTGKIH","created_at":"2026-06-30T02:18:10.746053+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/GUUTGKIHHCSG7VX2BYZVH3HK4Y","json":"https://pith.science/pith/GUUTGKIHHCSG7VX2BYZVH3HK4Y.json","graph_json":"https://pith.science/api/pith-number/GUUTGKIHHCSG7VX2BYZVH3HK4Y/graph.json","events_json":"https://pith.science/api/pith-number/GUUTGKIHHCSG7VX2BYZVH3HK4Y/events.json","paper":"https://pith.science/paper/GUUTGKIH"},"agent_actions":{"view_html":"https://pith.science/pith/GUUTGKIHHCSG7VX2BYZVH3HK4Y","download_json":"https://pith.science/pith/GUUTGKIHHCSG7VX2BYZVH3HK4Y.json","view_paper":"https://pith.science/paper/GUUTGKIH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30332&json=true","fetch_graph":"https://pith.science/api/pith-number/GUUTGKIHHCSG7VX2BYZVH3HK4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/GUUTGKIHHCSG7VX2BYZVH3HK4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUUTGKIHHCSG7VX2BYZVH3HK4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUUTGKIHHCSG7VX2BYZVH3HK4Y/action/storage_attestation","attest_author":"https://pith.science/pith/GUUTGKIHHCSG7VX2BYZVH3HK4Y/action/author_attestation","sign_citation":"https://pith.science/pith/GUUTGKIHHCSG7VX2BYZVH3HK4Y/action/citation_signature","submit_replication":"https://pith.science/pith/GUUTGKIHHCSG7VX2BYZVH3HK4Y/action/replication_record"}},"created_at":"2026-06-30T02:18:10.746053+00:00","updated_at":"2026-06-30T02:18:10.746053+00:00"}