{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FUQ7OMNJG64TAVTZ6AAY2ZRQ4V","short_pith_number":"pith:FUQ7OMNJ","schema_version":"1.0","canonical_sha256":"2d21f731a937b9305679f0018d6630e57685130f63c294304a8fcfc54c2e3436","source":{"kind":"arxiv","id":"2502.15894","version":3},"attestation_state":"computed","paper":{"title":"RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongxuan Li, Guande He, Hongzhou Zhu, Jun Zhu, Min Zhao, Yixiao Chen","submitted_at":"2025-02-21T19:28:05Z","abstract_excerpt":"Recent advancements in video generation have enabled models to synthesize high-quality, minute-long videos. However, generating even longer videos with temporal coherence remains a major challenge and existing length extrapolation methods lead to temporal repetition or motion deceleration. In this work, we systematically analyze the role of frequency components in positional embeddings and identify an intrinsic frequency that primarily governs extrapolation behavior. Based on this insight, we propose RIFLEx, a minimal yet effective approach that reduces the intrinsic frequency to suppress repe"},"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":"2502.15894","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-21T19:28:05Z","cross_cats_sorted":[],"title_canon_sha256":"7902db6f31b3943cc98c3452cf3c604d708598d510e2e8f5dc92bb807347713e","abstract_canon_sha256":"8604f6b630fb76c90409fe77abcca512d39bfc55679e28cfecae23077c32b9e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:50.785430Z","signature_b64":"kk2k+utaOmDZOq8TDUAYaTggx82NmF8iCZUmIEFIwa0F8QIGN5h5i/pW+QrzhFBsmDU9RwMlG/lQgjdL5hopAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d21f731a937b9305679f0018d6630e57685130f63c294304a8fcfc54c2e3436","last_reissued_at":"2026-07-05T11:49:50.784953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:50.784953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongxuan Li, Guande He, Hongzhou Zhu, Jun Zhu, Min Zhao, Yixiao Chen","submitted_at":"2025-02-21T19:28:05Z","abstract_excerpt":"Recent advancements in video generation have enabled models to synthesize high-quality, minute-long videos. However, generating even longer videos with temporal coherence remains a major challenge and existing length extrapolation methods lead to temporal repetition or motion deceleration. In this work, we systematically analyze the role of frequency components in positional embeddings and identify an intrinsic frequency that primarily governs extrapolation behavior. Based on this insight, we propose RIFLEx, a minimal yet effective approach that reduces the intrinsic frequency to suppress repe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15894","kind":"arxiv","version":3},"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/2502.15894/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":"2502.15894","created_at":"2026-07-05T11:49:50.785008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15894v3","created_at":"2026-07-05T11:49:50.785008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15894","created_at":"2026-07-05T11:49:50.785008+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUQ7OMNJG64T","created_at":"2026-07-05T11:49:50.785008+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUQ7OMNJG64TAVTZ","created_at":"2026-07-05T11:49:50.785008+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUQ7OMNJ","created_at":"2026-07-05T11:49:50.785008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22370","citing_title":"Towards Error-Free Long Video Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15141","citing_title":"Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31057","citing_title":"LVSA: Training-Free Sparse Attention for Long Video Diffusion","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31336","citing_title":"DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02214","citing_title":"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22668","citing_title":"SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02214","citing_title":"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20910","citing_title":"FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16003","citing_title":"Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18233","citing_title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2503.19325","citing_title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04678","citing_title":"Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02958","citing_title":"Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02283","citing_title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22622","citing_title":"LongLive: Real-time Interactive Long Video Generation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10045","citing_title":"ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06939","citing_title":"Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18215","citing_title":"Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V","json":"https://pith.science/pith/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V.json","graph_json":"https://pith.science/api/pith-number/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V/graph.json","events_json":"https://pith.science/api/pith-number/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V/events.json","paper":"https://pith.science/paper/FUQ7OMNJ"},"agent_actions":{"view_html":"https://pith.science/pith/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V","download_json":"https://pith.science/pith/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V.json","view_paper":"https://pith.science/paper/FUQ7OMNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15894&json=true","fetch_graph":"https://pith.science/api/pith-number/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V/graph.json","fetch_events":"https://pith.science/api/pith-number/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V/action/storage_attestation","attest_author":"https://pith.science/pith/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V/action/author_attestation","sign_citation":"https://pith.science/pith/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V/action/citation_signature","submit_replication":"https://pith.science/pith/FUQ7OMNJG64TAVTZ6AAY2ZRQ4V/action/replication_record"}},"created_at":"2026-07-05T11:49:50.785008+00:00","updated_at":"2026-07-05T11:49:50.785008+00:00"}