{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KAWI6CS5NBV5XWYEFFQFJ4CGFE","short_pith_number":"pith:KAWI6CS5","schema_version":"1.0","canonical_sha256":"502c8f0a5d686bdbdb04296054f04629262b8832d45bc6d9ecd346f1b92bbe8d","source":{"kind":"arxiv","id":"2607.06335","version":1},"attestation_state":"computed","paper":{"title":"Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jincheng Ying, Li Wenlin, Minghui Xu, Yinhao Xiao","submitted_at":"2026-07-07T14:30:24Z","abstract_excerpt":"Diffusion models generate high-quality images, but their inference cost comes from two sources: large denoising networks and repeated denoising steps. Existing compression pipelines usually attack these costs separately. Pruning reduces the network, but most pruning methods still rely on a long post-pruning retraining stage to recover a many-step sampler. Step distillation reduces the number of denoising steps, but it usually assumes a student that can already follow the teacher well enough to receive useful distillation gradients. This paper asks whether post-pruning retraining can be replace"},"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":"2607.06335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T14:30:24Z","cross_cats_sorted":[],"title_canon_sha256":"5e4f147bd3ee1ff1849dd4feef40c6bfa43347bb42c4b03b88151678b4873938","abstract_canon_sha256":"9941b383611da0af99ba5f5c8e63a6a940d19af3cf9e411926477b19b4958130"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:21.699187Z","signature_b64":"FpCW7XURZw/O5hhn3Wy9rRZHQrN3RoLdqY7t/2jjS6bVnDdCz2bsxerzp1v3ZK5CxMwZ4vE/Ml2CehKC95JWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"502c8f0a5d686bdbdb04296054f04629262b8832d45bc6d9ecd346f1b92bbe8d","last_reissued_at":"2026-07-08T01:19:21.698753Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:21.698753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jincheng Ying, Li Wenlin, Minghui Xu, Yinhao Xiao","submitted_at":"2026-07-07T14:30:24Z","abstract_excerpt":"Diffusion models generate high-quality images, but their inference cost comes from two sources: large denoising networks and repeated denoising steps. Existing compression pipelines usually attack these costs separately. Pruning reduces the network, but most pruning methods still rely on a long post-pruning retraining stage to recover a many-step sampler. Step distillation reduces the number of denoising steps, but it usually assumes a student that can already follow the teacher well enough to receive useful distillation gradients. This paper asks whether post-pruning retraining can be replace"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06335","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/2607.06335/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":"2607.06335","created_at":"2026-07-08T01:19:21.698813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06335v1","created_at":"2026-07-08T01:19:21.698813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06335","created_at":"2026-07-08T01:19:21.698813+00:00"},{"alias_kind":"pith_short_12","alias_value":"KAWI6CS5NBV5","created_at":"2026-07-08T01:19:21.698813+00:00"},{"alias_kind":"pith_short_16","alias_value":"KAWI6CS5NBV5XWYE","created_at":"2026-07-08T01:19:21.698813+00:00"},{"alias_kind":"pith_short_8","alias_value":"KAWI6CS5","created_at":"2026-07-08T01:19:21.698813+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/KAWI6CS5NBV5XWYEFFQFJ4CGFE","json":"https://pith.science/pith/KAWI6CS5NBV5XWYEFFQFJ4CGFE.json","graph_json":"https://pith.science/api/pith-number/KAWI6CS5NBV5XWYEFFQFJ4CGFE/graph.json","events_json":"https://pith.science/api/pith-number/KAWI6CS5NBV5XWYEFFQFJ4CGFE/events.json","paper":"https://pith.science/paper/KAWI6CS5"},"agent_actions":{"view_html":"https://pith.science/pith/KAWI6CS5NBV5XWYEFFQFJ4CGFE","download_json":"https://pith.science/pith/KAWI6CS5NBV5XWYEFFQFJ4CGFE.json","view_paper":"https://pith.science/paper/KAWI6CS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06335&json=true","fetch_graph":"https://pith.science/api/pith-number/KAWI6CS5NBV5XWYEFFQFJ4CGFE/graph.json","fetch_events":"https://pith.science/api/pith-number/KAWI6CS5NBV5XWYEFFQFJ4CGFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KAWI6CS5NBV5XWYEFFQFJ4CGFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KAWI6CS5NBV5XWYEFFQFJ4CGFE/action/storage_attestation","attest_author":"https://pith.science/pith/KAWI6CS5NBV5XWYEFFQFJ4CGFE/action/author_attestation","sign_citation":"https://pith.science/pith/KAWI6CS5NBV5XWYEFFQFJ4CGFE/action/citation_signature","submit_replication":"https://pith.science/pith/KAWI6CS5NBV5XWYEFFQFJ4CGFE/action/replication_record"}},"created_at":"2026-07-08T01:19:21.698813+00:00","updated_at":"2026-07-08T01:19:21.698813+00:00"}