{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6WDVKKSFBK4XGFSUC5SCV4BXMY","short_pith_number":"pith:6WDVKKSF","schema_version":"1.0","canonical_sha256":"f587552a450ab973165417642af0376610e9f47f9fca2987620064cce90f9923","source":{"kind":"arxiv","id":"2605.13111","version":1},"attestation_state":"computed","paper":{"title":"Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Pyramid Forcing assigns different KV cache lengths to three attention head types to reduce error accumulation in long autoregressive video generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guojie Luo, Jiawei Yang, Jiayi Luo, Jiayu Chen, Junbei Tang, Maoliang Li, Wenbiao Zhao, Xiang Chen, Zihao Zheng","submitted_at":"2026-05-13T07:23:02Z","abstract_excerpt":"Autoregressive video generation enables streaming and open-ended long video synthesis, but still suffers from long-term degradation caused by accumulated errors. Existing KVCache strategies usually apply unified historical-frame retention, implicitly assuming homogeneous historical dependencies across attention heads. We revisit historical-frame attention and reveal three distinct head types: Anchor Heads require broad long-range context, Wave Heads exhibit periodic temporal dependencies, and Veil Heads focus on initial and adjacent frames. Based on this finding, we propose Pyramid Forcing, a "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.13111","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T07:23:02Z","cross_cats_sorted":[],"title_canon_sha256":"ce189f10a6b255df28ffdde68e05f4dfca67e591ce6a0c610c34cf63fb17e514","abstract_canon_sha256":"75348fc516cdb834c97cc03a6a77d15ec404b5a3b0f3efe1bd8c934986d90c1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:58.115900Z","signature_b64":"lbEOQAr1gnrIRUbCXhhje0/MjhCWzZSJ0UHNJbNO1/aCNNRMzLgII2DXgns3+mJKNP36U+f431hsxryCcMFHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f587552a450ab973165417642af0376610e9f47f9fca2987620064cce90f9923","last_reissued_at":"2026-05-18T03:08:58.115445Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:58.115445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Pyramid Forcing assigns different KV cache lengths to three attention head types to reduce error accumulation in long autoregressive video generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guojie Luo, Jiawei Yang, Jiayi Luo, Jiayu Chen, Junbei Tang, Maoliang Li, Wenbiao Zhao, Xiang Chen, Zihao Zheng","submitted_at":"2026-05-13T07:23:02Z","abstract_excerpt":"Autoregressive video generation enables streaming and open-ended long video synthesis, but still suffers from long-term degradation caused by accumulated errors. Existing KVCache strategies usually apply unified historical-frame retention, implicitly assuming homogeneous historical dependencies across attention heads. We revisit historical-frame attention and reveal three distinct head types: Anchor Heads require broad long-range context, Wave Heads exhibit periodic temporal dependencies, and Veil Heads focus on initial and adjacent frames. Based on this finding, we propose Pyramid Forcing, a "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Pyramid Forcing consistently improves long-horizon generation quality on VBench-Long, increasing the 60-second Self Forcing score from 77.87 to 81.21 while enhancing motion dynamics, visual fidelity, and semantic consistency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The three head types (Anchor, Wave, Veil) are stable across different models and datasets and can be reliably identified offline without retraining or runtime overhead.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Pyramid Forcing classifies attention heads into Anchor, Wave, and Veil types and applies type-specific KV cache policies to improve long-horizon autoregressive video generation quality.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Pyramid Forcing assigns different KV cache lengths to three attention head types to reduce error accumulation in long autoregressive video generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0034745f686999cf8d3a57fd914a790d63029398a276cab7a25fe2884107ad44"},"source":{"id":"2605.13111","kind":"arxiv","version":1},"verdict":{"id":"a47233f5-e04b-434f-bff1-a76a4301e02d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:45:28.528497Z","strongest_claim":"Pyramid Forcing consistently improves long-horizon generation quality on VBench-Long, increasing the 60-second Self Forcing score from 77.87 to 81.21 while enhancing motion dynamics, visual fidelity, and semantic consistency.","one_line_summary":"Pyramid Forcing classifies attention heads into Anchor, Wave, and Veil types and applies type-specific KV cache policies to improve long-horizon autoregressive video generation quality.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The three head types (Anchor, Wave, Veil) are stable across different models and datasets and can be reliably identified offline without retraining or runtime overhead.","pith_extraction_headline":"Pyramid Forcing assigns different KV cache lengths to three attention head types to reduce error accumulation in long autoregressive video generation."},"references":{"count":37,"sample":[{"doi":"","year":2025,"title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","work_id":"53e58ef9-7932-4b83-b757-34ac14db3e0f","ref_index":1,"cited_arxiv_id":"2506.08009","is_internal_anchor":true},{"doi":"","year":2025,"title":"MAGI-1: Autoregressive Video Generation at Scale","work_id":"25e8bd3d-e51c-43ae-8126-4ea6ecdb3321","ref_index":2,"cited_arxiv_id":"2505.13211","is_internal_anchor":true},{"doi":"","year":2026,"title":"Causal forcing: Autoregressive diffusion distillation done right for high-quality real- time interactive video generation","work_id":"04f67f5b-e79a-4ad9-8e90-763e5e54bd3d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Scalable diffusion models with transformers","work_id":"3e203719-f1d3-4517-959c-98e6121f3e23","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","ref_index":5,"cited_arxiv_id":"2503.20314","is_internal_anchor":true}],"resolved_work":37,"snapshot_sha256":"0a92017860eae31d2d678829bc712e5e95c682d41cfe1ca05185fbb2b7ccdfd3","internal_anchors":10},"formal_canon":{"evidence_count":2,"snapshot_sha256":"cdf72e11bb671562156e1ed3f09472f4931f15d2709f30fe7a0712cb7d21041a"},"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":"2605.13111","created_at":"2026-05-18T03:08:58.115512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13111v1","created_at":"2026-05-18T03:08:58.115512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13111","created_at":"2026-05-18T03:08:58.115512+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WDVKKSFBK4X","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WDVKKSFBK4XGFSU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WDVKKSF","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WDVKKSFBK4XGFSUC5SCV4BXMY","json":"https://pith.science/pith/6WDVKKSFBK4XGFSUC5SCV4BXMY.json","graph_json":"https://pith.science/api/pith-number/6WDVKKSFBK4XGFSUC5SCV4BXMY/graph.json","events_json":"https://pith.science/api/pith-number/6WDVKKSFBK4XGFSUC5SCV4BXMY/events.json","paper":"https://pith.science/paper/6WDVKKSF"},"agent_actions":{"view_html":"https://pith.science/pith/6WDVKKSFBK4XGFSUC5SCV4BXMY","download_json":"https://pith.science/pith/6WDVKKSFBK4XGFSUC5SCV4BXMY.json","view_paper":"https://pith.science/paper/6WDVKKSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13111&json=true","fetch_graph":"https://pith.science/api/pith-number/6WDVKKSFBK4XGFSUC5SCV4BXMY/graph.json","fetch_events":"https://pith.science/api/pith-number/6WDVKKSFBK4XGFSUC5SCV4BXMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WDVKKSFBK4XGFSUC5SCV4BXMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WDVKKSFBK4XGFSUC5SCV4BXMY/action/storage_attestation","attest_author":"https://pith.science/pith/6WDVKKSFBK4XGFSUC5SCV4BXMY/action/author_attestation","sign_citation":"https://pith.science/pith/6WDVKKSFBK4XGFSUC5SCV4BXMY/action/citation_signature","submit_replication":"https://pith.science/pith/6WDVKKSFBK4XGFSUC5SCV4BXMY/action/replication_record"}},"created_at":"2026-05-18T03:08:58.115512+00:00","updated_at":"2026-05-18T03:08:58.115512+00:00"}