{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:767WIGSQZ4OG7KNY55U6LHJMOA","short_pith_number":"pith:767WIGSQ","schema_version":"1.0","canonical_sha256":"ffbf641a50cf1c6fa9b8ef69e59d2c7005f126370096546f121873415e80116f","source":{"kind":"arxiv","id":"2506.01380","version":2},"attestation_state":"computed","paper":{"title":"Playing with Transformer at 30+ FPS via Next-Frame Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di He, Jiang Bian, Jiayi Xu, Junliang Guo, Tianyu He, Xinle Cheng","submitted_at":"2025-06-02T07:16:01Z","abstract_excerpt":"Autoregressive video models offer distinct advantages over bidirectional diffusion models in creating interactive video content and supporting streaming applications with arbitrary duration. In this work, we present Next-Frame Diffusion (NFD), an autoregressive diffusion transformer that incorporates block-wise causal attention, enabling iterative sampling and efficient inference via parallel token generation within each frame. Nonetheless, achieving real-time video generation remains a significant challenge for such models, primarily due to the high computational cost associated with diffusio"},"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":"2506.01380","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T07:16:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3b271267b578dbc3175f5d7c5fd480710ab68969a1fadfdffd0487cbfe02da8","abstract_canon_sha256":"a3cae98590e8f03af1c2f17230bd183aa4331ee24e2c88a31699260433e36788"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:45.876312Z","signature_b64":"Cec84hbj5VPkI8a7Egn98VLgNvST/aT8oHR+91I7a+qOH+9V1yVfzDpOKluUTgqiaOdWuQTicfJybAnRyDrsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffbf641a50cf1c6fa9b8ef69e59d2c7005f126370096546f121873415e80116f","last_reissued_at":"2026-07-05T11:31:45.875838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:45.875838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Playing with Transformer at 30+ FPS via Next-Frame Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Di He, Jiang Bian, Jiayi Xu, Junliang Guo, Tianyu He, Xinle Cheng","submitted_at":"2025-06-02T07:16:01Z","abstract_excerpt":"Autoregressive video models offer distinct advantages over bidirectional diffusion models in creating interactive video content and supporting streaming applications with arbitrary duration. In this work, we present Next-Frame Diffusion (NFD), an autoregressive diffusion transformer that incorporates block-wise causal attention, enabling iterative sampling and efficient inference via parallel token generation within each frame. Nonetheless, achieving real-time video generation remains a significant challenge for such models, primarily due to the high computational cost associated with diffusio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01380","kind":"arxiv","version":2},"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/2506.01380/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":"2506.01380","created_at":"2026-07-05T11:31:45.875897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01380v2","created_at":"2026-07-05T11:31:45.875897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01380","created_at":"2026-07-05T11:31:45.875897+00:00"},{"alias_kind":"pith_short_12","alias_value":"767WIGSQZ4OG","created_at":"2026-07-05T11:31:45.875897+00:00"},{"alias_kind":"pith_short_16","alias_value":"767WIGSQZ4OG7KNY","created_at":"2026-07-05T11:31:45.875897+00:00"},{"alias_kind":"pith_short_8","alias_value":"767WIGSQ","created_at":"2026-07-05T11:31:45.875897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20708","citing_title":"Rethinking Cross-Layer Information Routing in Diffusion Transformers","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20708","citing_title":"Rethinking Cross-Layer Information Routing in Diffusion Transformers","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07982","citing_title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13009","citing_title":"Matrix-game 2.0: An open-source real-time and streaming interactive world model","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09527","citing_title":"Envisioning the Future, One Step at a Time","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":245,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/767WIGSQZ4OG7KNY55U6LHJMOA","json":"https://pith.science/pith/767WIGSQZ4OG7KNY55U6LHJMOA.json","graph_json":"https://pith.science/api/pith-number/767WIGSQZ4OG7KNY55U6LHJMOA/graph.json","events_json":"https://pith.science/api/pith-number/767WIGSQZ4OG7KNY55U6LHJMOA/events.json","paper":"https://pith.science/paper/767WIGSQ"},"agent_actions":{"view_html":"https://pith.science/pith/767WIGSQZ4OG7KNY55U6LHJMOA","download_json":"https://pith.science/pith/767WIGSQZ4OG7KNY55U6LHJMOA.json","view_paper":"https://pith.science/paper/767WIGSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01380&json=true","fetch_graph":"https://pith.science/api/pith-number/767WIGSQZ4OG7KNY55U6LHJMOA/graph.json","fetch_events":"https://pith.science/api/pith-number/767WIGSQZ4OG7KNY55U6LHJMOA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/767WIGSQZ4OG7KNY55U6LHJMOA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/767WIGSQZ4OG7KNY55U6LHJMOA/action/storage_attestation","attest_author":"https://pith.science/pith/767WIGSQZ4OG7KNY55U6LHJMOA/action/author_attestation","sign_citation":"https://pith.science/pith/767WIGSQZ4OG7KNY55U6LHJMOA/action/citation_signature","submit_replication":"https://pith.science/pith/767WIGSQZ4OG7KNY55U6LHJMOA/action/replication_record"}},"created_at":"2026-07-05T11:31:45.875897+00:00","updated_at":"2026-07-05T11:31:45.875897+00:00"}