{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G5OT2NBTLUBQXIAUIF5VMNDECW","short_pith_number":"pith:G5OT2NBT","schema_version":"1.0","canonical_sha256":"375d3d34335d030ba014417b56346415af9182dcf15dc6299a5fb55d4e4f39aa","source":{"kind":"arxiv","id":"2605.15141","version":1},"attestation_state":"computed","paper":{"title":"Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bokai Yan, Chongxuan Li, Hongzhou Zhu, Jun Zhu, Kaiwen Zheng, Min Zhao, Xiao Yang, Xinyuan Li, Zihan Zhou","submitted_at":"2026-05-14T17:46:36Z","abstract_excerpt":"Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong results in the chunk-wise 4-step regime by distilling bidirectional base models into few-step AR students, but they remain limited by coarse response granularity and non-negligible sampling latency. In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps. In this regime, we identify the initialization of a few-step AR student as the key bottleneck: existing strategies"},"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":"2605.15141","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T17:46:36Z","cross_cats_sorted":[],"title_canon_sha256":"95a2baa4daf5c3e3dd11034398884c52e61e9d9b47a9c331759c36c967193517","abstract_canon_sha256":"b5a155d861d2387870d17e9aede1e3c45b0d208bda5e3b6870399297bafb8459"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:54.004028Z","signature_b64":"2lpMdrJZ5gX5U1u+z+SDTnf5UcoPMPvt5YbVn0155b3RM+d9f338opwd7lQqWBhr1M9OlCl9hdUyCv4acyHUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"375d3d34335d030ba014417b56346415af9182dcf15dc6299a5fb55d4e4f39aa","last_reissued_at":"2026-05-17T23:38:54.003169Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:54.003169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bokai Yan, Chongxuan Li, Hongzhou Zhu, Jun Zhu, Kaiwen Zheng, Min Zhao, Xiao Yang, Xinyuan Li, Zihan Zhou","submitted_at":"2026-05-14T17:46:36Z","abstract_excerpt":"Real-time interactive video generation requires low-latency, streaming, and controllable rollout. Existing autoregressive (AR) diffusion distillation methods have achieved strong results in the chunk-wise 4-step regime by distilling bidirectional base models into few-step AR students, but they remain limited by coarse response granularity and non-negligible sampling latency. In this paper, we study a more aggressive setting: frame-wise autoregression with only 1--2 sampling steps. In this regime, we identify the initialization of a few-step AR student as the key bottleneck: existing strategies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15141","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":""},"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":"2605.15141","created_at":"2026-05-17T23:38:54.003343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15141v1","created_at":"2026-05-17T23:38:54.003343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15141","created_at":"2026-05-17T23:38:54.003343+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5OT2NBTLUBQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5OT2NBTLUBQXIAU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5OT2NBT","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23458","citing_title":"One-Forcing: Towards Stable One-Step Autoregressive Video Generation","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5OT2NBTLUBQXIAUIF5VMNDECW","json":"https://pith.science/pith/G5OT2NBTLUBQXIAUIF5VMNDECW.json","graph_json":"https://pith.science/api/pith-number/G5OT2NBTLUBQXIAUIF5VMNDECW/graph.json","events_json":"https://pith.science/api/pith-number/G5OT2NBTLUBQXIAUIF5VMNDECW/events.json","paper":"https://pith.science/paper/G5OT2NBT"},"agent_actions":{"view_html":"https://pith.science/pith/G5OT2NBTLUBQXIAUIF5VMNDECW","download_json":"https://pith.science/pith/G5OT2NBTLUBQXIAUIF5VMNDECW.json","view_paper":"https://pith.science/paper/G5OT2NBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15141&json=true","fetch_graph":"https://pith.science/api/pith-number/G5OT2NBTLUBQXIAUIF5VMNDECW/graph.json","fetch_events":"https://pith.science/api/pith-number/G5OT2NBTLUBQXIAUIF5VMNDECW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5OT2NBTLUBQXIAUIF5VMNDECW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5OT2NBTLUBQXIAUIF5VMNDECW/action/storage_attestation","attest_author":"https://pith.science/pith/G5OT2NBTLUBQXIAUIF5VMNDECW/action/author_attestation","sign_citation":"https://pith.science/pith/G5OT2NBTLUBQXIAUIF5VMNDECW/action/citation_signature","submit_replication":"https://pith.science/pith/G5OT2NBTLUBQXIAUIF5VMNDECW/action/replication_record"}},"created_at":"2026-05-17T23:38:54.003343+00:00","updated_at":"2026-05-17T23:38:54.003343+00:00"}