{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2BNY7G4UGEZAYGGXR5LIDJJFQJ","short_pith_number":"pith:2BNY7G4U","schema_version":"1.0","canonical_sha256":"d05b8f9b9431320c18d78f5681a52582448273778d5fd42c39e6a1092e275562","source":{"kind":"arxiv","id":"2605.19729","version":1},"attestation_state":"computed","paper":{"title":"LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hyunsoo Han, Jaejun Yoo, Sangyeop Yeo","submitted_at":"2026-05-19T12:03:53Z","abstract_excerpt":"We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully mimic. To address this problem, we propose a coarse-to-fine distillation framework with LInear FiTtingbased distillation (LIFT) and Piecewise Local Adaptive Coefficient Estimation (PLACE). First, LIFT decomposes the objective into a \"coarse\" alignment and a \"fine\" refinement. The student is then trained on coarse alignment before proceeding to hard refineme"},"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":"2605.19729","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T12:03:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c826cbbe1e9fbf6781fc3a064c633870c96cac24353ac42675416cd399c8085","abstract_canon_sha256":"1ce4043018406f953561cabf1d4ca6de81dad659375ca2eb88c758bd6e308386"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:11.316194Z","signature_b64":"khHxOK1AlPEnj22skdTDflonqNf3OUWuReks354E3KBYUS3i8YPvj7raAYe2S8MgRZbBf6wBuXuJk671B3V2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d05b8f9b9431320c18d78f5681a52582448273778d5fd42c39e6a1092e275562","last_reissued_at":"2026-05-20T01:06:11.315695Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:11.315695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hyunsoo Han, Jaejun Yoo, Sangyeop Yeo","submitted_at":"2026-05-19T12:03:53Z","abstract_excerpt":"We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully mimic. To address this problem, we propose a coarse-to-fine distillation framework with LInear FiTtingbased distillation (LIFT) and Piecewise Local Adaptive Coefficient Estimation (PLACE). First, LIFT decomposes the objective into a \"coarse\" alignment and a \"fine\" refinement. The student is then trained on coarse alignment before proceeding to hard refineme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19729","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/2605.19729/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":"2605.19729","created_at":"2026-05-20T01:06:11.315776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19729v1","created_at":"2026-05-20T01:06:11.315776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19729","created_at":"2026-05-20T01:06:11.315776+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BNY7G4UGEZA","created_at":"2026-05-20T01:06:11.315776+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BNY7G4UGEZAYGGX","created_at":"2026-05-20T01:06:11.315776+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BNY7G4U","created_at":"2026-05-20T01:06:11.315776+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/2BNY7G4UGEZAYGGXR5LIDJJFQJ","json":"https://pith.science/pith/2BNY7G4UGEZAYGGXR5LIDJJFQJ.json","graph_json":"https://pith.science/api/pith-number/2BNY7G4UGEZAYGGXR5LIDJJFQJ/graph.json","events_json":"https://pith.science/api/pith-number/2BNY7G4UGEZAYGGXR5LIDJJFQJ/events.json","paper":"https://pith.science/paper/2BNY7G4U"},"agent_actions":{"view_html":"https://pith.science/pith/2BNY7G4UGEZAYGGXR5LIDJJFQJ","download_json":"https://pith.science/pith/2BNY7G4UGEZAYGGXR5LIDJJFQJ.json","view_paper":"https://pith.science/paper/2BNY7G4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19729&json=true","fetch_graph":"https://pith.science/api/pith-number/2BNY7G4UGEZAYGGXR5LIDJJFQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2BNY7G4UGEZAYGGXR5LIDJJFQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BNY7G4UGEZAYGGXR5LIDJJFQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BNY7G4UGEZAYGGXR5LIDJJFQJ/action/storage_attestation","attest_author":"https://pith.science/pith/2BNY7G4UGEZAYGGXR5LIDJJFQJ/action/author_attestation","sign_citation":"https://pith.science/pith/2BNY7G4UGEZAYGGXR5LIDJJFQJ/action/citation_signature","submit_replication":"https://pith.science/pith/2BNY7G4UGEZAYGGXR5LIDJJFQJ/action/replication_record"}},"created_at":"2026-05-20T01:06:11.315776+00:00","updated_at":"2026-05-20T01:06:11.315776+00:00"}