{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SOG76RN3TQ5Y4YJFP72WN7Q7ID","short_pith_number":"pith:SOG76RN3","schema_version":"1.0","canonical_sha256":"938dff45bb9c3b8e61257ff566fe1f40e46e1e7bbc09df06a3ea787119790ac0","source":{"kind":"arxiv","id":"2404.13686","version":3},"attestation_state":"computed","paper":{"title":"Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiacheng Zhang, Jie Wu, Pan Xie, Xing Wang, Xin Xia, Xuefeng Xiao, Yanzuo Lu, Yuxi Ren","submitted_at":"2024-04-21T15:16:05Z","abstract_excerpt":"Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize into two distinct aspects: i) ODE Trajectory Preservation; and ii) ODE Trajectory Reformulation. However, these approaches suffer from severe performance degradation or domain shifts. To address these limitations, we propose Hyper-SD, a novel framework that synergistically amalgamates the advantages of ODE Trajectory Preservation and Reformulation, while ma"},"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":"2404.13686","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-21T15:16:05Z","cross_cats_sorted":[],"title_canon_sha256":"0eaf25350d49280fb85c76884fd8aff2fc7518f139acee5cef238c40358cc285","abstract_canon_sha256":"f2c27679260b411803fc7dd08d12110232a597db3711502b916f600f99ed5d21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:12.822120Z","signature_b64":"wOGvObZeCjSFY1Q+6OEVNiDYi9htuTlspIzDLumscZtx5SeCT0JL0PWsE0l2RULzuGoXJqDfoudU/PUKMG5YDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"938dff45bb9c3b8e61257ff566fe1f40e46e1e7bbc09df06a3ea787119790ac0","last_reissued_at":"2026-07-05T09:30:12.821643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:12.821643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiacheng Zhang, Jie Wu, Pan Xie, Xing Wang, Xin Xia, Xuefeng Xiao, Yanzuo Lu, Yuxi Ren","submitted_at":"2024-04-21T15:16:05Z","abstract_excerpt":"Recently, a series of diffusion-aware distillation algorithms have emerged to alleviate the computational overhead associated with the multi-step inference process of Diffusion Models (DMs). Current distillation techniques often dichotomize into two distinct aspects: i) ODE Trajectory Preservation; and ii) ODE Trajectory Reformulation. However, these approaches suffer from severe performance degradation or domain shifts. To address these limitations, we propose Hyper-SD, a novel framework that synergistically amalgamates the advantages of ODE Trajectory Preservation and Reformulation, while ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13686","kind":"arxiv","version":3},"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/2404.13686/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":"2404.13686","created_at":"2026-07-05T09:30:12.821700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13686v3","created_at":"2026-07-05T09:30:12.821700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13686","created_at":"2026-07-05T09:30:12.821700+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOG76RN3TQ5Y","created_at":"2026-07-05T09:30:12.821700+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOG76RN3TQ5Y4YJF","created_at":"2026-07-05T09:30:12.821700+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOG76RN3","created_at":"2026-07-05T09:30:12.821700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05204","citing_title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16259","citing_title":"Systematic Optimization of Real-Time Diffusion Model Inference on Apple M3 Ultra","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05204","citing_title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03118","citing_title":"Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04018","citing_title":"1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05204","citing_title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14910","citing_title":"Reward-Aware Trajectory Shaping for Few-step Visual Generation","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SOG76RN3TQ5Y4YJFP72WN7Q7ID","json":"https://pith.science/pith/SOG76RN3TQ5Y4YJFP72WN7Q7ID.json","graph_json":"https://pith.science/api/pith-number/SOG76RN3TQ5Y4YJFP72WN7Q7ID/graph.json","events_json":"https://pith.science/api/pith-number/SOG76RN3TQ5Y4YJFP72WN7Q7ID/events.json","paper":"https://pith.science/paper/SOG76RN3"},"agent_actions":{"view_html":"https://pith.science/pith/SOG76RN3TQ5Y4YJFP72WN7Q7ID","download_json":"https://pith.science/pith/SOG76RN3TQ5Y4YJFP72WN7Q7ID.json","view_paper":"https://pith.science/paper/SOG76RN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13686&json=true","fetch_graph":"https://pith.science/api/pith-number/SOG76RN3TQ5Y4YJFP72WN7Q7ID/graph.json","fetch_events":"https://pith.science/api/pith-number/SOG76RN3TQ5Y4YJFP72WN7Q7ID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOG76RN3TQ5Y4YJFP72WN7Q7ID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOG76RN3TQ5Y4YJFP72WN7Q7ID/action/storage_attestation","attest_author":"https://pith.science/pith/SOG76RN3TQ5Y4YJFP72WN7Q7ID/action/author_attestation","sign_citation":"https://pith.science/pith/SOG76RN3TQ5Y4YJFP72WN7Q7ID/action/citation_signature","submit_replication":"https://pith.science/pith/SOG76RN3TQ5Y4YJFP72WN7Q7ID/action/replication_record"}},"created_at":"2026-07-05T09:30:12.821700+00:00","updated_at":"2026-07-05T09:30:12.821700+00:00"}