{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4ZM2Y5HC7O2635VXU7EL2IUHAQ","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":"0c5d8e816c8ebd79bc31c62422d122469362b4d08e10b6836e83d80feff792f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T17:59:23Z","title_canon_sha256":"15890fe64fd37e99f89ead68949fbd5e31076b201d81e2457d24b0155b68ecc5"},"schema_version":"1.0","source":{"id":"2607.14088","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14088","created_at":"2026-07-16T01:23:23Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14088v1","created_at":"2026-07-16T01:23:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14088","created_at":"2026-07-16T01:23:23Z"},{"alias_kind":"pith_short_12","alias_value":"4ZM2Y5HC7O26","created_at":"2026-07-16T01:23:23Z"},{"alias_kind":"pith_short_16","alias_value":"4ZM2Y5HC7O2635VX","created_at":"2026-07-16T01:23:23Z"},{"alias_kind":"pith_short_8","alias_value":"4ZM2Y5HC","created_at":"2026-07-16T01:23:23Z"}],"graph_snapshots":[{"event_id":"sha256:52fc72372a4688630cb785afd35cd6e1e974edfbe112fd1369501f01209cc681","target":"graph","created_at":"2026-07-16T01:23:23Z","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/2607.14088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video generative models commonly rely on latent spaces learned by 3D Variational Autoencoders (3D-VAEs). However, conventional 3D-VAEs are mainly optimized for pixel-level reconstruction, which can limit the semantic and spatio-temporal structure captured by their latents. Meanwhile, Video Foundation Models (VFMs) such as V-JEPA 2 and VideoMAEv2 show strong video understanding capabilities, yet whether their frozen representations can be transformed into compact, reconstruction-capable, and generation-friendly video latents remains largely unexplored. We answer this question with VideoRAE, a r","authors_text":"Junchao Huang, Junfeng Wu, Li Jiang, Xinting Hu, Zhihao Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T17:59:23Z","title":"VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14088","kind":"arxiv","version":1},"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:fc070408f4dc87d352ae869c9e4176d9367b44d4f3690dd39a11fdf44025adc4","target":"record","created_at":"2026-07-16T01:23:23Z","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":"0c5d8e816c8ebd79bc31c62422d122469362b4d08e10b6836e83d80feff792f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T17:59:23Z","title_canon_sha256":"15890fe64fd37e99f89ead68949fbd5e31076b201d81e2457d24b0155b68ecc5"},"schema_version":"1.0","source":{"id":"2607.14088","kind":"arxiv","version":1}},"canonical_sha256":"e659ac74e2fbb5edf6b7a7c8bd2287041b132806db0818f09ad104bbb8ec591f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e659ac74e2fbb5edf6b7a7c8bd2287041b132806db0818f09ad104bbb8ec591f","first_computed_at":"2026-07-16T01:23:23.890432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:23:23.890432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LsmatYBTCzitIO2Lm8s1Y74XHljOIMmKFeiRPu1JdVgtRLRi9p/vGWvYmDX5xKfWxDgI9pgYErvMXq/FZn6ICA==","signature_status":"signed_v1","signed_at":"2026-07-16T01:23:23.891304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14088","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc070408f4dc87d352ae869c9e4176d9367b44d4f3690dd39a11fdf44025adc4","sha256:52fc72372a4688630cb785afd35cd6e1e974edfbe112fd1369501f01209cc681"],"state_sha256":"096be07d117a006474754fcb5784aba4ec73b18bd0ff5d17f5b6ce08d528aee1"}