{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JTUH5G7UKWPZAU4TKKBPSFELYR","short_pith_number":"pith:JTUH5G7U","schema_version":"1.0","canonical_sha256":"4ce87e9bf4559f9053935282f9148bc441faa53f886e1b0e4bf697565f23a601","source":{"kind":"arxiv","id":"2605.17019","version":1},"attestation_state":"computed","paper":{"title":"StreamingEffect: Real-Time Human-Centric Video Effect Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"StreamingEffect distills a bidirectional video editing teacher into a causal student that generates real-time human-centric effects at 720p on one GPU.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Liu, Mike Zheng Shou, Yiren Song, Yuxin Jiang","submitted_at":"2026-05-16T14:45:32Z","abstract_excerpt":"Streaming video effect generation is highly desirable for live human-centric applications such as e-commerce streaming, entertainment, and vlogging, yet remains difficult due to the lack of suitable data and deployable editing models. Unlike generic video generation, this task requires real-time video-to-video editing that adds expressive effects while preserving human identity, background content, and temporal consistency. Existing acceleration efforts mainly focus on text-to-video generation, while efficient distillation for video editing remains largely underexplored. In this paper, we pres"},"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":"2605.17019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T14:45:32Z","cross_cats_sorted":[],"title_canon_sha256":"7a66992e954ce0a12a360cf4df962621e1ac4f8ee3d2542318c0216abd0f03c7","abstract_canon_sha256":"51fac3cacaf3b5c2def4c9ab83b412f2eff5cb5c36f61c93f2b58a56862d3e65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:36.292024Z","signature_b64":"xTAQCHtVswbsMPBH93Yq1ZuBxKImRypOxReyDXQeKjMoR+z+0Bg5eWGWtfoftWUGlaFIhWkq2ACj1jXYMSuWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ce87e9bf4559f9053935282f9148bc441faa53f886e1b0e4bf697565f23a601","last_reissued_at":"2026-05-20T00:03:36.291221Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:36.291221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StreamingEffect: Real-Time Human-Centric Video Effect Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"StreamingEffect distills a bidirectional video editing teacher into a causal student that generates real-time human-centric effects at 720p on one GPU.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Liu, Mike Zheng Shou, Yiren Song, Yuxin Jiang","submitted_at":"2026-05-16T14:45:32Z","abstract_excerpt":"Streaming video effect generation is highly desirable for live human-centric applications such as e-commerce streaming, entertainment, and vlogging, yet remains difficult due to the lack of suitable data and deployable editing models. Unlike generic video generation, this task requires real-time video-to-video editing that adds expressive effects while preserving human identity, background content, and temporal consistency. Existing acceleration efforts mainly focus on text-to-video generation, while efficient distillation for video editing remains largely underexplored. In this paper, we pres"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments show that our method enables real-time, high-quality 720p video editing on a single H200 GPU.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The distilled causal student model preserves human identity, background content, and temporal consistency at a level comparable to the bidirectional teacher when operating in a streaming, one-pass regime.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"StreamingEffect distills a bidirectional video editing teacher into a causal student that generates real-time human-centric effects at 720p on one GPU.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3131e32abd230328f0ef3a3fcd9e86cbfaf7c0c6f76a5b4e17844e7d08c04c50"},"source":{"id":"2605.17019","kind":"arxiv","version":1},"verdict":{"id":"65c6f842-82d8-4662-8d03-648b905e58cc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T20:08:23.611917Z","strongest_claim":"Experiments show that our method enables real-time, high-quality 720p video editing on a single H200 GPU.","one_line_summary":"StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The distilled causal student model preserves human identity, background content, and temporal consistency at a level comparable to the bidirectional teacher when operating in a streaming, one-pass regime.","pith_extraction_headline":"StreamingEffect distills a bidirectional video editing teacher into a causal student that generates real-time human-centric effects at 720p on one GPU."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17019/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T20:31:18.997724Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:21:39.355563Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T19:49:48.647200Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T18:51:58.740334Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.184578Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:24.867885Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"30ad1c56ef2b9e47653d417c8b7e6fbcd093061d1e4c0ea09808978ee22e6611"},"references":{"count":77,"sample":[{"doi":"","year":2024,"title":"Lumiere: A space-time diffusion model for video generation","work_id":"26709c55-8dfb-456d-adaf-744519782327","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","work_id":"4f68eada-27e3-437a-a2fe-6e4ca524d0d3","ref_index":2,"cited_arxiv_id":"2311.15127","is_internal_anchor":true},{"doi":"","year":2023,"title":"Align your latents: High-resolution video synthesis with latent diffusion models","work_id":"83645ec7-6155-4a2a-b13a-2e728f342ea1","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Instructpix2pix: Learning to follow image editing instructions","work_id":"182396b0-39b5-4e35-adfd-c6dbe856535f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Video generation models as world simulators","work_id":"50001333-33e1-40d2-b890-a00116cf2c1b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":77,"snapshot_sha256":"96d8e4642e129c1878b1a1c0b5f5413fd27c259e1762995054241d53613f5194","internal_anchors":25},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8be8de35ceed35cfbb053933df8186565ffbf95a395703e60baa04cb628d8b13"},"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":"2605.17019","created_at":"2026-05-20T00:03:36.291349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17019v1","created_at":"2026-05-20T00:03:36.291349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17019","created_at":"2026-05-20T00:03:36.291349+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTUH5G7UKWPZ","created_at":"2026-05-20T00:03:36.291349+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTUH5G7UKWPZAU4T","created_at":"2026-05-20T00:03:36.291349+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTUH5G7U","created_at":"2026-05-20T00:03:36.291349+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/JTUH5G7UKWPZAU4TKKBPSFELYR","json":"https://pith.science/pith/JTUH5G7UKWPZAU4TKKBPSFELYR.json","graph_json":"https://pith.science/api/pith-number/JTUH5G7UKWPZAU4TKKBPSFELYR/graph.json","events_json":"https://pith.science/api/pith-number/JTUH5G7UKWPZAU4TKKBPSFELYR/events.json","paper":"https://pith.science/paper/JTUH5G7U"},"agent_actions":{"view_html":"https://pith.science/pith/JTUH5G7UKWPZAU4TKKBPSFELYR","download_json":"https://pith.science/pith/JTUH5G7UKWPZAU4TKKBPSFELYR.json","view_paper":"https://pith.science/paper/JTUH5G7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17019&json=true","fetch_graph":"https://pith.science/api/pith-number/JTUH5G7UKWPZAU4TKKBPSFELYR/graph.json","fetch_events":"https://pith.science/api/pith-number/JTUH5G7UKWPZAU4TKKBPSFELYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTUH5G7UKWPZAU4TKKBPSFELYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTUH5G7UKWPZAU4TKKBPSFELYR/action/storage_attestation","attest_author":"https://pith.science/pith/JTUH5G7UKWPZAU4TKKBPSFELYR/action/author_attestation","sign_citation":"https://pith.science/pith/JTUH5G7UKWPZAU4TKKBPSFELYR/action/citation_signature","submit_replication":"https://pith.science/pith/JTUH5G7UKWPZAU4TKKBPSFELYR/action/replication_record"}},"created_at":"2026-05-20T00:03:36.291349+00:00","updated_at":"2026-05-20T00:03:36.291349+00:00"}