{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JWDVE4LZFR4HM7GIGKY7XLXB6B","short_pith_number":"pith:JWDVE4LZ","schema_version":"1.0","canonical_sha256":"4d875271792c78767cc832b1fbaee1f057f02a8fc5301b9b053746b834341a99","source":{"kind":"arxiv","id":"2506.14168","version":2},"attestation_state":"computed","paper":{"title":"VideoMAR: Autoregressive Video Generatio with Continuous Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Biao Gong, Dandan Zheng, Feng Zhao, Hangjie Yuan, Hu Yu, Jingdong Chen, Kecheng Zheng, Weilong Chai","submitted_at":"2025-06-17T04:08:18Z","abstract_excerpt":"Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored. In this paper, we propose \\textbf{VideoMAR}, a concise and efficient decoder-only autoregressive image-to-video model with continuous tokens, composing temporal frame-by-frame and spatial masked generation. We first identify temporal causality and spatial bi-directionality as the first principle of video AR models, and propose the next-frame diffusion loss for the integration of mask and video generation. Besides, "},"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":"2506.14168","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T04:08:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b32697dd546868df138075ba10a3de69bad685376110b07ff8a322bac08f11f","abstract_canon_sha256":"1f1a3930ad895dc80c2a5031388d72f11ac4e8a3e9fe222764fdb51830608395"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:30.914821Z","signature_b64":"OljYYvOq4TsOOcG7ttBjAJk+bRxhex5KKe7vdKcacjAMQjJd/JBq+03czDCRRC6whm9EAbo1pIUEEr+w7OecBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d875271792c78767cc832b1fbaee1f057f02a8fc5301b9b053746b834341a99","last_reissued_at":"2026-07-05T11:23:30.914312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:30.914312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoMAR: Autoregressive Video Generatio with Continuous Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Biao Gong, Dandan Zheng, Feng Zhao, Hangjie Yuan, Hu Yu, Jingdong Chen, Kecheng Zheng, Weilong Chai","submitted_at":"2025-06-17T04:08:18Z","abstract_excerpt":"Masked-based autoregressive models have demonstrated promising image generation capability in continuous space. However, their potential for video generation remains under-explored. In this paper, we propose \\textbf{VideoMAR}, a concise and efficient decoder-only autoregressive image-to-video model with continuous tokens, composing temporal frame-by-frame and spatial masked generation. We first identify temporal causality and spatial bi-directionality as the first principle of video AR models, and propose the next-frame diffusion loss for the integration of mask and video generation. Besides, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14168","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/2506.14168/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":"2506.14168","created_at":"2026-07-05T11:23:30.914374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14168v2","created_at":"2026-07-05T11:23:30.914374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14168","created_at":"2026-07-05T11:23:30.914374+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWDVE4LZFR4H","created_at":"2026-07-05T11:23:30.914374+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWDVE4LZFR4HM7GI","created_at":"2026-07-05T11:23:30.914374+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWDVE4LZ","created_at":"2026-07-05T11:23:30.914374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03578","citing_title":"Diffusing in the Right Space: A Systematic Study of Latent Diffusability","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31326","citing_title":"Bridging Video Understanding and Generation in a Unified Framework","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27964","citing_title":"Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30083","citing_title":"Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06966","citing_title":"MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":167,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04461","citing_title":"Stream-T1: Test-Time Scaling for Streaming Video Generation","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWDVE4LZFR4HM7GIGKY7XLXB6B","json":"https://pith.science/pith/JWDVE4LZFR4HM7GIGKY7XLXB6B.json","graph_json":"https://pith.science/api/pith-number/JWDVE4LZFR4HM7GIGKY7XLXB6B/graph.json","events_json":"https://pith.science/api/pith-number/JWDVE4LZFR4HM7GIGKY7XLXB6B/events.json","paper":"https://pith.science/paper/JWDVE4LZ"},"agent_actions":{"view_html":"https://pith.science/pith/JWDVE4LZFR4HM7GIGKY7XLXB6B","download_json":"https://pith.science/pith/JWDVE4LZFR4HM7GIGKY7XLXB6B.json","view_paper":"https://pith.science/paper/JWDVE4LZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14168&json=true","fetch_graph":"https://pith.science/api/pith-number/JWDVE4LZFR4HM7GIGKY7XLXB6B/graph.json","fetch_events":"https://pith.science/api/pith-number/JWDVE4LZFR4HM7GIGKY7XLXB6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWDVE4LZFR4HM7GIGKY7XLXB6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWDVE4LZFR4HM7GIGKY7XLXB6B/action/storage_attestation","attest_author":"https://pith.science/pith/JWDVE4LZFR4HM7GIGKY7XLXB6B/action/author_attestation","sign_citation":"https://pith.science/pith/JWDVE4LZFR4HM7GIGKY7XLXB6B/action/citation_signature","submit_replication":"https://pith.science/pith/JWDVE4LZFR4HM7GIGKY7XLXB6B/action/replication_record"}},"created_at":"2026-07-05T11:23:30.914374+00:00","updated_at":"2026-07-05T11:23:30.914374+00:00"}