{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KLJPPLODCZDIK72FWG5LQLSHQ6","short_pith_number":"pith:KLJPPLOD","schema_version":"1.0","canonical_sha256":"52d2f7adc31646857f45b1bab82e47879d180dbbe9aacb73306568afb75432d6","source":{"kind":"arxiv","id":"2506.18999","version":1},"attestation_state":"computed","paper":{"title":"Diffusion Transformer-to-Mamba Distillation for High-Resolution Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Difan Liu, Feng Liu, Jiebo Luo, Long Mai, Yicong Hong, Yuan Yao","submitted_at":"2025-06-23T18:01:19Z","abstract_excerpt":"The quadratic computational complexity of self-attention in diffusion transformers (DiT) introduces substantial computational costs in high-resolution image generation. While the linear-complexity Mamba model emerges as a potential alternative, direct Mamba training remains empirically challenging. To address this issue, this paper introduces diffusion transformer-to-mamba distillation (T2MD), forming an efficient training pipeline that facilitates the transition from the self-attention-based transformer to the linear complexity state-space model Mamba. We establish a diffusion self-attention "},"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":"2506.18999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T18:01:19Z","cross_cats_sorted":[],"title_canon_sha256":"b1a3db33ac97afed233cdea11e3fb4ec1879305b555ba46e23172a275438d1e8","abstract_canon_sha256":"2e35640e3b2440df55b39f580d4e715ac8c9c90d3bc7c6cf788c36e39cce1e1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:07.704880Z","signature_b64":"gx+XnznoV48L2baiD72kHJbRCrfuSFZZ4jYMlENHpFZBiSoJAAzmVULawJc2Szad0RcFG4Oq1pAEgLf63HtMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52d2f7adc31646857f45b1bab82e47879d180dbbe9aacb73306568afb75432d6","last_reissued_at":"2026-07-05T11:26:07.704343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:07.704343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Transformer-to-Mamba Distillation for High-Resolution Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Difan Liu, Feng Liu, Jiebo Luo, Long Mai, Yicong Hong, Yuan Yao","submitted_at":"2025-06-23T18:01:19Z","abstract_excerpt":"The quadratic computational complexity of self-attention in diffusion transformers (DiT) introduces substantial computational costs in high-resolution image generation. While the linear-complexity Mamba model emerges as a potential alternative, direct Mamba training remains empirically challenging. To address this issue, this paper introduces diffusion transformer-to-mamba distillation (T2MD), forming an efficient training pipeline that facilitates the transition from the self-attention-based transformer to the linear complexity state-space model Mamba. We establish a diffusion self-attention "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18999","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/2506.18999/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":"2506.18999","created_at":"2026-07-05T11:26:07.704414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18999v1","created_at":"2026-07-05T11:26:07.704414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18999","created_at":"2026-07-05T11:26:07.704414+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLJPPLODCZDI","created_at":"2026-07-05T11:26:07.704414+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLJPPLODCZDIK72F","created_at":"2026-07-05T11:26:07.704414+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLJPPLOD","created_at":"2026-07-05T11:26:07.704414+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/KLJPPLODCZDIK72FWG5LQLSHQ6","json":"https://pith.science/pith/KLJPPLODCZDIK72FWG5LQLSHQ6.json","graph_json":"https://pith.science/api/pith-number/KLJPPLODCZDIK72FWG5LQLSHQ6/graph.json","events_json":"https://pith.science/api/pith-number/KLJPPLODCZDIK72FWG5LQLSHQ6/events.json","paper":"https://pith.science/paper/KLJPPLOD"},"agent_actions":{"view_html":"https://pith.science/pith/KLJPPLODCZDIK72FWG5LQLSHQ6","download_json":"https://pith.science/pith/KLJPPLODCZDIK72FWG5LQLSHQ6.json","view_paper":"https://pith.science/paper/KLJPPLOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18999&json=true","fetch_graph":"https://pith.science/api/pith-number/KLJPPLODCZDIK72FWG5LQLSHQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/KLJPPLODCZDIK72FWG5LQLSHQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLJPPLODCZDIK72FWG5LQLSHQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLJPPLODCZDIK72FWG5LQLSHQ6/action/storage_attestation","attest_author":"https://pith.science/pith/KLJPPLODCZDIK72FWG5LQLSHQ6/action/author_attestation","sign_citation":"https://pith.science/pith/KLJPPLODCZDIK72FWG5LQLSHQ6/action/citation_signature","submit_replication":"https://pith.science/pith/KLJPPLODCZDIK72FWG5LQLSHQ6/action/replication_record"}},"created_at":"2026-07-05T11:26:07.704414+00:00","updated_at":"2026-07-05T11:26:07.704414+00:00"}