{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K3LGAECFFGFP6OMAGW6JG53GIC","short_pith_number":"pith:K3LGAECF","schema_version":"1.0","canonical_sha256":"56d6601045298aff398035bc93776640afc0ee46c16aa8de4e262f105d4b5418","source":{"kind":"arxiv","id":"2605.26632","version":1},"attestation_state":"computed","paper":{"title":"RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenhao Xie, Hanlin Tang, Kan Liu, Lan Tao, Lin Qu, Xing Cong","submitted_at":"2026-05-26T07:09:49Z","abstract_excerpt":"Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and distillation, semi-structured sparsity, which can nearly halve FLOPs, remains underexplored. A key reason is that most existing approaches focus on weight sparsification, and pruning 50% of the weights can remove critical model capacity and degrade generation quality. Our study, however, shows that DiT activations are intrinsically sparse and significantly more robust to N:M semi-structured sparsification than weights. Mo"},"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":"2605.26632","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T07:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"05c951691ea1f405371150e44eade47f1c77dfbe2dfc69f0edf06abbbe3abc70","abstract_canon_sha256":"75fc435a95790cdc7d371c13e1a848a3e0960955c59eb7056f2ad00985ce255e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:03.018310Z","signature_b64":"qSRhhwyOxiZzOUoum8Nt2FBeScYNfVqFbDTlUYH8tDA4nIVjGeptMsc/yQOJg8FSrMLMYiZm9W0kgb4u69J5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56d6601045298aff398035bc93776640afc0ee46c16aa8de4e262f105d4b5418","last_reissued_at":"2026-05-27T01:06:03.017564Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:03.017564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenhao Xie, Hanlin Tang, Kan Liu, Lan Tao, Lin Qu, Xing Cong","submitted_at":"2026-05-26T07:09:49Z","abstract_excerpt":"Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and distillation, semi-structured sparsity, which can nearly halve FLOPs, remains underexplored. A key reason is that most existing approaches focus on weight sparsification, and pruning 50% of the weights can remove critical model capacity and degrade generation quality. Our study, however, shows that DiT activations are intrinsically sparse and significantly more robust to N:M semi-structured sparsification than weights. Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26632","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/2605.26632/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":"2605.26632","created_at":"2026-05-27T01:06:03.017657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26632v1","created_at":"2026-05-27T01:06:03.017657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26632","created_at":"2026-05-27T01:06:03.017657+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3LGAECFFGFP","created_at":"2026-05-27T01:06:03.017657+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3LGAECFFGFP6OMA","created_at":"2026-05-27T01:06:03.017657+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3LGAECF","created_at":"2026-05-27T01:06:03.017657+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/K3LGAECFFGFP6OMAGW6JG53GIC","json":"https://pith.science/pith/K3LGAECFFGFP6OMAGW6JG53GIC.json","graph_json":"https://pith.science/api/pith-number/K3LGAECFFGFP6OMAGW6JG53GIC/graph.json","events_json":"https://pith.science/api/pith-number/K3LGAECFFGFP6OMAGW6JG53GIC/events.json","paper":"https://pith.science/paper/K3LGAECF"},"agent_actions":{"view_html":"https://pith.science/pith/K3LGAECFFGFP6OMAGW6JG53GIC","download_json":"https://pith.science/pith/K3LGAECFFGFP6OMAGW6JG53GIC.json","view_paper":"https://pith.science/paper/K3LGAECF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26632&json=true","fetch_graph":"https://pith.science/api/pith-number/K3LGAECFFGFP6OMAGW6JG53GIC/graph.json","fetch_events":"https://pith.science/api/pith-number/K3LGAECFFGFP6OMAGW6JG53GIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3LGAECFFGFP6OMAGW6JG53GIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3LGAECFFGFP6OMAGW6JG53GIC/action/storage_attestation","attest_author":"https://pith.science/pith/K3LGAECFFGFP6OMAGW6JG53GIC/action/author_attestation","sign_citation":"https://pith.science/pith/K3LGAECFFGFP6OMAGW6JG53GIC/action/citation_signature","submit_replication":"https://pith.science/pith/K3LGAECFFGFP6OMAGW6JG53GIC/action/replication_record"}},"created_at":"2026-05-27T01:06:03.017657+00:00","updated_at":"2026-05-27T01:06:03.017657+00:00"}