{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JWDVE4LZFR4HM7GIGKY7XLXB6B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1f1a3930ad895dc80c2a5031388d72f11ac4e8a3e9fe222764fdb51830608395","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T04:08:18Z","title_canon_sha256":"2b32697dd546868df138075ba10a3de69bad685376110b07ff8a322bac08f11f"},"schema_version":"1.0","source":{"id":"2506.14168","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14168","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14168v2","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14168","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_12","alias_value":"JWDVE4LZFR4H","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_16","alias_value":"JWDVE4LZFR4HM7GI","created_at":"2026-07-05T11:23:30Z"},{"alias_kind":"pith_short_8","alias_value":"JWDVE4LZ","created_at":"2026-07-05T11:23:30Z"}],"graph_snapshots":[{"event_id":"sha256:0c5161c3dff0e5e00ba06af0e46d4a675e93b9b1894414666114f164ae7162f3","target":"graph","created_at":"2026-07-05T11:23:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.14168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Biao Gong, Dandan Zheng, Feng Zhao, Hangjie Yuan, Hu Yu, Jingdong Chen, Kecheng Zheng, Weilong Chai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T04:08:18Z","title":"VideoMAR: Autoregressive Video Generatio with Continuous Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14168","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:26be7adfb2fe3842719c2321025389fef92ce397666cccd49caa513cbdd7527e","target":"record","created_at":"2026-07-05T11:23:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1f1a3930ad895dc80c2a5031388d72f11ac4e8a3e9fe222764fdb51830608395","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T04:08:18Z","title_canon_sha256":"2b32697dd546868df138075ba10a3de69bad685376110b07ff8a322bac08f11f"},"schema_version":"1.0","source":{"id":"2506.14168","kind":"arxiv","version":2}},"canonical_sha256":"4d875271792c78767cc832b1fbaee1f057f02a8fc5301b9b053746b834341a99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d875271792c78767cc832b1fbaee1f057f02a8fc5301b9b053746b834341a99","first_computed_at":"2026-07-05T11:23:30.914312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:30.914312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OljYYvOq4TsOOcG7ttBjAJk+bRxhex5KKe7vdKcacjAMQjJd/JBq+03czDCRRC6whm9EAbo1pIUEEr+w7OecBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:30.914821Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14168","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26be7adfb2fe3842719c2321025389fef92ce397666cccd49caa513cbdd7527e","sha256:0c5161c3dff0e5e00ba06af0e46d4a675e93b9b1894414666114f164ae7162f3"],"state_sha256":"80849f5d3ef86b30e16fff25715ba8aeefbcf8456356e38ba06f26c3431c08a5"}