{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:46Q6NTKZIPGLOSRKRGAKKQELBK","short_pith_number":"pith:46Q6NTKZ","schema_version":"1.0","canonical_sha256":"e7a1e6cd5943ccb74a2a8980a5408b0a8880233abb7bdce8358cdba93347a3ff","source":{"kind":"arxiv","id":"2606.26778","version":1},"attestation_state":"computed","paper":{"title":"LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wang Shen, Xiao-Ping Zhang, Xuyue Huang, Zhe Chen","submitted_at":"2026-06-25T09:12:51Z","abstract_excerpt":"Diffusion Transformers (DiTs) have driven substantial progress in image and video generation but suffer from prohibitive computational costs. Feature caching accelerates inference by reusing intermediate representations. Existing methods rely on historical features for implementation simplicity, yet suffer from severe error accumulation at high acceleration ratios. To address this limitation, we investigate the nature of the requisite feature correction. We demonstrate that the optimal calibration update is characterized by a shared low-rank subspace across diverse prompts. Guided by this stru"},"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":"2606.26778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T09:12:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b8871a52b0fb8d5eee560a3ac54cd8a9c3a81b7b9234771a08b5b973378fba22","abstract_canon_sha256":"13e6c91ab2e5211bcca8c2853247fe2c5fff384b4915d8a373b6aa416c3c36cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:59.485599Z","signature_b64":"nHZPiT4zbxMvCn8R8S+6BghgtTY1zTMunbro6pqoRZaKcV8apX6DicM/JdoJXITUGz7cJqopZh5WyBJHsWDOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7a1e6cd5943ccb74a2a8980a5408b0a8880233abb7bdce8358cdba93347a3ff","last_reissued_at":"2026-06-26T01:15:59.485202Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:59.485202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wang Shen, Xiao-Ping Zhang, Xuyue Huang, Zhe Chen","submitted_at":"2026-06-25T09:12:51Z","abstract_excerpt":"Diffusion Transformers (DiTs) have driven substantial progress in image and video generation but suffer from prohibitive computational costs. Feature caching accelerates inference by reusing intermediate representations. Existing methods rely on historical features for implementation simplicity, yet suffer from severe error accumulation at high acceleration ratios. To address this limitation, we investigate the nature of the requisite feature correction. We demonstrate that the optimal calibration update is characterized by a shared low-rank subspace across diverse prompts. Guided by this stru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26778","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/2606.26778/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":"2606.26778","created_at":"2026-06-26T01:15:59.485256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26778v1","created_at":"2026-06-26T01:15:59.485256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26778","created_at":"2026-06-26T01:15:59.485256+00:00"},{"alias_kind":"pith_short_12","alias_value":"46Q6NTKZIPGL","created_at":"2026-06-26T01:15:59.485256+00:00"},{"alias_kind":"pith_short_16","alias_value":"46Q6NTKZIPGLOSRK","created_at":"2026-06-26T01:15:59.485256+00:00"},{"alias_kind":"pith_short_8","alias_value":"46Q6NTKZ","created_at":"2026-06-26T01:15:59.485256+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/46Q6NTKZIPGLOSRKRGAKKQELBK","json":"https://pith.science/pith/46Q6NTKZIPGLOSRKRGAKKQELBK.json","graph_json":"https://pith.science/api/pith-number/46Q6NTKZIPGLOSRKRGAKKQELBK/graph.json","events_json":"https://pith.science/api/pith-number/46Q6NTKZIPGLOSRKRGAKKQELBK/events.json","paper":"https://pith.science/paper/46Q6NTKZ"},"agent_actions":{"view_html":"https://pith.science/pith/46Q6NTKZIPGLOSRKRGAKKQELBK","download_json":"https://pith.science/pith/46Q6NTKZIPGLOSRKRGAKKQELBK.json","view_paper":"https://pith.science/paper/46Q6NTKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26778&json=true","fetch_graph":"https://pith.science/api/pith-number/46Q6NTKZIPGLOSRKRGAKKQELBK/graph.json","fetch_events":"https://pith.science/api/pith-number/46Q6NTKZIPGLOSRKRGAKKQELBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46Q6NTKZIPGLOSRKRGAKKQELBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46Q6NTKZIPGLOSRKRGAKKQELBK/action/storage_attestation","attest_author":"https://pith.science/pith/46Q6NTKZIPGLOSRKRGAKKQELBK/action/author_attestation","sign_citation":"https://pith.science/pith/46Q6NTKZIPGLOSRKRGAKKQELBK/action/citation_signature","submit_replication":"https://pith.science/pith/46Q6NTKZIPGLOSRKRGAKKQELBK/action/replication_record"}},"created_at":"2026-06-26T01:15:59.485256+00:00","updated_at":"2026-06-26T01:15:59.485256+00:00"}