{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L2J7LDNUWZI4MODFSHDMU55QIA","short_pith_number":"pith:L2J7LDNU","schema_version":"1.0","canonical_sha256":"5e93f58db4b651c6386591c6ca77b04023eb60052df241526e9d0a796bae31d9","source":{"kind":"arxiv","id":"2606.06060","version":1},"attestation_state":"computed","paper":{"title":"ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aibek Alanov, Aleksandr Oganov, Denis Rakitin, Eva Neudachina, Ilya Bykov, Kirill Struminsky, Mishan Aliev","submitted_at":"2026-06-04T11:59:56Z","abstract_excerpt":"Modern diffusion models generate high-quality images and videos, but their iterative denoising process makes inference expensive. Feature caching accelerates sampling by reusing or predicting intermediate activations across neighboring denoising steps, exploiting the redundancy of computations along the reverse trajectory. In this work, we focus on the caching schedule: selecting which denoising steps should be fully recomputed. Existing schedules are either fixed (e.g. uniform) or chosen adaptively from per-step error heuristics; in both cases, the actual compute cost is a side-effect of hand"},"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":"2606.06060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-04T11:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"41b1a037d943831e7613c4f08c5e520e7fcf6d94a4bab62a28777a104f90f826","abstract_canon_sha256":"e889fa0b0c0007990891d3355fb2d38f89e3f9519b6920da689ed8a6d64f5389"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:31.811090Z","signature_b64":"7RRJPo9Rk5M4ENs28Zfc77qz/9Mb5dcho0Lu4WvR/+R+pUMD4cE/16Jsf6HKnKz+VH6OoFaKCzigI8jhVSkLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e93f58db4b651c6386591c6ca77b04023eb60052df241526e9d0a796bae31d9","last_reissued_at":"2026-06-05T01:15:31.810673Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:31.810673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aibek Alanov, Aleksandr Oganov, Denis Rakitin, Eva Neudachina, Ilya Bykov, Kirill Struminsky, Mishan Aliev","submitted_at":"2026-06-04T11:59:56Z","abstract_excerpt":"Modern diffusion models generate high-quality images and videos, but their iterative denoising process makes inference expensive. Feature caching accelerates sampling by reusing or predicting intermediate activations across neighboring denoising steps, exploiting the redundancy of computations along the reverse trajectory. In this work, we focus on the caching schedule: selecting which denoising steps should be fully recomputed. Existing schedules are either fixed (e.g. uniform) or chosen adaptively from per-step error heuristics; in both cases, the actual compute cost is a side-effect of hand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06060","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/2606.06060/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":"2606.06060","created_at":"2026-06-05T01:15:31.810738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06060v1","created_at":"2026-06-05T01:15:31.810738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06060","created_at":"2026-06-05T01:15:31.810738+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2J7LDNUWZI4","created_at":"2026-06-05T01:15:31.810738+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2J7LDNUWZI4MODF","created_at":"2026-06-05T01:15:31.810738+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2J7LDNU","created_at":"2026-06-05T01:15:31.810738+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/L2J7LDNUWZI4MODFSHDMU55QIA","json":"https://pith.science/pith/L2J7LDNUWZI4MODFSHDMU55QIA.json","graph_json":"https://pith.science/api/pith-number/L2J7LDNUWZI4MODFSHDMU55QIA/graph.json","events_json":"https://pith.science/api/pith-number/L2J7LDNUWZI4MODFSHDMU55QIA/events.json","paper":"https://pith.science/paper/L2J7LDNU"},"agent_actions":{"view_html":"https://pith.science/pith/L2J7LDNUWZI4MODFSHDMU55QIA","download_json":"https://pith.science/pith/L2J7LDNUWZI4MODFSHDMU55QIA.json","view_paper":"https://pith.science/paper/L2J7LDNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06060&json=true","fetch_graph":"https://pith.science/api/pith-number/L2J7LDNUWZI4MODFSHDMU55QIA/graph.json","fetch_events":"https://pith.science/api/pith-number/L2J7LDNUWZI4MODFSHDMU55QIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2J7LDNUWZI4MODFSHDMU55QIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2J7LDNUWZI4MODFSHDMU55QIA/action/storage_attestation","attest_author":"https://pith.science/pith/L2J7LDNUWZI4MODFSHDMU55QIA/action/author_attestation","sign_citation":"https://pith.science/pith/L2J7LDNUWZI4MODFSHDMU55QIA/action/citation_signature","submit_replication":"https://pith.science/pith/L2J7LDNUWZI4MODFSHDMU55QIA/action/replication_record"}},"created_at":"2026-06-05T01:15:31.810738+00:00","updated_at":"2026-06-05T01:15:31.810738+00:00"}