{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A7YNOQJWLYDVAJM45IP6VLSRJD","short_pith_number":"pith:A7YNOQJW","schema_version":"1.0","canonical_sha256":"07f0d741365e0750259cea1feaae5148e9b74478aa6f6ff9f07cc399e17f9789","source":{"kind":"arxiv","id":"2607.18510","version":1},"attestation_state":"computed","paper":{"title":"DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Micha\\\"el Gharbi, Yossi Gandelsman, Yunpeng Bai","submitted_at":"2026-07-20T21:08:56Z","abstract_excerpt":"Diffusion Transformers achieve strong image generation performance, but most operate in compressed latent spaces. Pixel-space diffusion avoids this information loss, yet existing approaches map each raw image patch to a single token, forcing one representation to handle both global communication and fine-grained details. We address this issue by proposing a new architecture, \\textbf{DuSPiT}, a \\textbf{Du}al-branch \\textbf{S}ub\\textbf{P}atch \\textbf{Pi}xel \\textbf{T}ransformer. This model separates global structural reasoning from local appearance modeling. DuSPiT uses a compact base branch for"},"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":"2607.18510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T21:08:56Z","cross_cats_sorted":[],"title_canon_sha256":"393c7a194e2d2111fe82607048b4f465c79c49c94a3f8f3d4ac01232a34f70ea","abstract_canon_sha256":"ede3d427127a0892f86304cd76782851f30e01a2db5f32db31fe5b123fe2270b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:52.108216Z","signature_b64":"GmHQgMdeIyJVMWhE31mTCLoBmbgLeP4yoLUd9B/WsfEG+g+hxnbmSHjxS0/rZNGF3HftIZMPEZeG1/xkvYAPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07f0d741365e0750259cea1feaae5148e9b74478aa6f6ff9f07cc399e17f9789","last_reissued_at":"2026-07-22T00:22:52.107372Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:52.107372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DuSPiT: Dual-Branch Sub-Patch Pixel Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Micha\\\"el Gharbi, Yossi Gandelsman, Yunpeng Bai","submitted_at":"2026-07-20T21:08:56Z","abstract_excerpt":"Diffusion Transformers achieve strong image generation performance, but most operate in compressed latent spaces. Pixel-space diffusion avoids this information loss, yet existing approaches map each raw image patch to a single token, forcing one representation to handle both global communication and fine-grained details. We address this issue by proposing a new architecture, \\textbf{DuSPiT}, a \\textbf{Du}al-branch \\textbf{S}ub\\textbf{P}atch \\textbf{Pi}xel \\textbf{T}ransformer. This model separates global structural reasoning from local appearance modeling. DuSPiT uses a compact base branch for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18510","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/2607.18510/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":"2607.18510","created_at":"2026-07-22T00:22:52.107807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18510v1","created_at":"2026-07-22T00:22:52.107807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18510","created_at":"2026-07-22T00:22:52.107807+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7YNOQJWLYDV","created_at":"2026-07-22T00:22:52.107807+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7YNOQJWLYDVAJM4","created_at":"2026-07-22T00:22:52.107807+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7YNOQJW","created_at":"2026-07-22T00:22:52.107807+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/A7YNOQJWLYDVAJM45IP6VLSRJD","json":"https://pith.science/pith/A7YNOQJWLYDVAJM45IP6VLSRJD.json","graph_json":"https://pith.science/api/pith-number/A7YNOQJWLYDVAJM45IP6VLSRJD/graph.json","events_json":"https://pith.science/api/pith-number/A7YNOQJWLYDVAJM45IP6VLSRJD/events.json","paper":"https://pith.science/paper/A7YNOQJW"},"agent_actions":{"view_html":"https://pith.science/pith/A7YNOQJWLYDVAJM45IP6VLSRJD","download_json":"https://pith.science/pith/A7YNOQJWLYDVAJM45IP6VLSRJD.json","view_paper":"https://pith.science/paper/A7YNOQJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18510&json=true","fetch_graph":"https://pith.science/api/pith-number/A7YNOQJWLYDVAJM45IP6VLSRJD/graph.json","fetch_events":"https://pith.science/api/pith-number/A7YNOQJWLYDVAJM45IP6VLSRJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7YNOQJWLYDVAJM45IP6VLSRJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7YNOQJWLYDVAJM45IP6VLSRJD/action/storage_attestation","attest_author":"https://pith.science/pith/A7YNOQJWLYDVAJM45IP6VLSRJD/action/author_attestation","sign_citation":"https://pith.science/pith/A7YNOQJWLYDVAJM45IP6VLSRJD/action/citation_signature","submit_replication":"https://pith.science/pith/A7YNOQJWLYDVAJM45IP6VLSRJD/action/replication_record"}},"created_at":"2026-07-22T00:22:52.107807+00:00","updated_at":"2026-07-22T00:22:52.107807+00:00"}