{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W23LKNSEHOP6OPC7EFTPZBFFG5","short_pith_number":"pith:W23LKNSE","schema_version":"1.0","canonical_sha256":"b6b6b536443b9fe73c5f2166fc84a537664ab6ce1de681234aeb13c8d653ff1b","source":{"kind":"arxiv","id":"2605.15741","version":1},"attestation_state":"computed","paper":{"title":"HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Chen, Jingling Fu, Junshi Huang, Lichen Ma, Xinyuan Shan, Yan Li, Yu He, Zipeng Guo","submitted_at":"2026-05-15T08:51:55Z","abstract_excerpt":"Pixel-space diffusion models bypass the reconstruction bottleneck of Variational Autoencoders (VAEs) but face a fundamental \"granularity dilemma\": capturing global semantics favors large patch scales, while generating high-fidelity details demands fine-grained inputs. To address this issue, we propose HyperDiT, a unified framework establishing Hyper-Connected Cross-Scale Interactions to bridge the semantic and pixel manifold. Diverging from injecting semantics by AdaLN, HyperDiT utilizes Cross-Attention mechanisms, enabling fine-grained tokens to query multi-level semantic anchors globally. To"},"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":"2605.15741","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T08:51:55Z","cross_cats_sorted":[],"title_canon_sha256":"c921adb521978d007dd24beff3e56ab3bccc6370dfc54a4bec30b27bea9ef2a6","abstract_canon_sha256":"41cdbb39516befe92194b0c8870589324448344e073bfb35ee5e9f25bf6f083f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:15.787608Z","signature_b64":"MqZ0htCCXe0uRpqeMKKzjCYKp8hE4P8zoY04lD6Ckm0d+EZ3Gf48uVkIFwdt9gDH3hZohDiYu/geus8hu/FEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6b6b536443b9fe73c5f2166fc84a537664ab6ce1de681234aeb13c8d653ff1b","last_reissued_at":"2026-05-20T00:01:15.786780Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:15.786780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Chen, Jingling Fu, Junshi Huang, Lichen Ma, Xinyuan Shan, Yan Li, Yu He, Zipeng Guo","submitted_at":"2026-05-15T08:51:55Z","abstract_excerpt":"Pixel-space diffusion models bypass the reconstruction bottleneck of Variational Autoencoders (VAEs) but face a fundamental \"granularity dilemma\": capturing global semantics favors large patch scales, while generating high-fidelity details demands fine-grained inputs. To address this issue, we propose HyperDiT, a unified framework establishing Hyper-Connected Cross-Scale Interactions to bridge the semantic and pixel manifold. Diverging from injecting semantics by AdaLN, HyperDiT utilizes Cross-Attention mechanisms, enabling fine-grained tokens to query multi-level semantic anchors globally. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15741","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/2605.15741/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:23.895009Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.981280Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"1c5e30bdab5436b248fb48fe03f55ed652ebdc0f64b225dc52a07873777f1d20"},"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":"2605.15741","created_at":"2026-05-20T00:01:15.786915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15741v1","created_at":"2026-05-20T00:01:15.786915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15741","created_at":"2026-05-20T00:01:15.786915+00:00"},{"alias_kind":"pith_short_12","alias_value":"W23LKNSEHOP6","created_at":"2026-05-20T00:01:15.786915+00:00"},{"alias_kind":"pith_short_16","alias_value":"W23LKNSEHOP6OPC7","created_at":"2026-05-20T00:01:15.786915+00:00"},{"alias_kind":"pith_short_8","alias_value":"W23LKNSE","created_at":"2026-05-20T00:01:15.786915+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/W23LKNSEHOP6OPC7EFTPZBFFG5","json":"https://pith.science/pith/W23LKNSEHOP6OPC7EFTPZBFFG5.json","graph_json":"https://pith.science/api/pith-number/W23LKNSEHOP6OPC7EFTPZBFFG5/graph.json","events_json":"https://pith.science/api/pith-number/W23LKNSEHOP6OPC7EFTPZBFFG5/events.json","paper":"https://pith.science/paper/W23LKNSE"},"agent_actions":{"view_html":"https://pith.science/pith/W23LKNSEHOP6OPC7EFTPZBFFG5","download_json":"https://pith.science/pith/W23LKNSEHOP6OPC7EFTPZBFFG5.json","view_paper":"https://pith.science/paper/W23LKNSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15741&json=true","fetch_graph":"https://pith.science/api/pith-number/W23LKNSEHOP6OPC7EFTPZBFFG5/graph.json","fetch_events":"https://pith.science/api/pith-number/W23LKNSEHOP6OPC7EFTPZBFFG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W23LKNSEHOP6OPC7EFTPZBFFG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W23LKNSEHOP6OPC7EFTPZBFFG5/action/storage_attestation","attest_author":"https://pith.science/pith/W23LKNSEHOP6OPC7EFTPZBFFG5/action/author_attestation","sign_citation":"https://pith.science/pith/W23LKNSEHOP6OPC7EFTPZBFFG5/action/citation_signature","submit_replication":"https://pith.science/pith/W23LKNSEHOP6OPC7EFTPZBFFG5/action/replication_record"}},"created_at":"2026-05-20T00:01:15.786915+00:00","updated_at":"2026-05-20T00:01:15.786915+00:00"}