{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4SP77SIT3VWDW4WHQGQKWCTJXZ","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":"66b76aab849bb2c4a565893c3c20e2f68b90ccf364f5fd97e2476ba1dc5d615a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T17:54:10Z","title_canon_sha256":"654fbb6b0584009a750287dceb7dad732f5c407ec8cd616453ffd1ef9e8214ff"},"schema_version":"1.0","source":{"id":"2507.19468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19468","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19468v1","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19468","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"4SP77SIT3VWD","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"pith_short_16","alias_value":"4SP77SIT3VWDW4WH","created_at":"2026-07-05T11:43:25Z"},{"alias_kind":"pith_short_8","alias_value":"4SP77SIT","created_at":"2026-07-05T11:43:25Z"}],"graph_snapshots":[{"event_id":"sha256:5f4cb0ee9a023f9608cdb662df7e14016d63d99c9f7559806a6cae642d1024dd","target":"graph","created_at":"2026-07-05T11:43:25Z","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/2507.19468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present DINO-world, a powerful generalist video world model trained to predict future frames in the latent space of DINOv2. By leveraging a pre-trained image encoder and training a future predictor on a large-scale uncurated video dataset, DINO-world learns the temporal dynamics of diverse scenes, from driving and indoor scenes to simulated environments. We show that DINO-world outperforms previous models on a variety of video prediction benchmarks, e.g. segmentation and depth forecasting, and demonstrates strong understanding of intuitive physics. Furthermore, we show that it is possible t","authors_text":"Basile Terver, Federico Baldassarre, Francisco Massa, Marc Szafraniec, Maximilian Seitzer, Patrick Labatut, Piotr Bojanowski, Vasil Khalidov, Yann LeCun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T17:54:10Z","title":"Back to the Features: DINO as a Foundation for Video World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19468","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:eb9f616020c90f1f9eb2bd404d6d0e8e1c4277946e14ce29e5a93fb96ba7c6cc","target":"record","created_at":"2026-07-05T11:43:25Z","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":"66b76aab849bb2c4a565893c3c20e2f68b90ccf364f5fd97e2476ba1dc5d615a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T17:54:10Z","title_canon_sha256":"654fbb6b0584009a750287dceb7dad732f5c407ec8cd616453ffd1ef9e8214ff"},"schema_version":"1.0","source":{"id":"2507.19468","kind":"arxiv","version":1}},"canonical_sha256":"e49fffc913dd6c3b72c781a0ab0a69be4293675defac070939f30f8d816f6d5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e49fffc913dd6c3b72c781a0ab0a69be4293675defac070939f30f8d816f6d5a","first_computed_at":"2026-07-05T11:43:25.794231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:25.794231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u2423307jQjwkTWEtNfu2DYEHTyEFdbgH3EhVOVwfDJWHqBiN3eKok0rK0777MnLWMWtW8+0wnMW+bDcLgZ0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:25.794711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb9f616020c90f1f9eb2bd404d6d0e8e1c4277946e14ce29e5a93fb96ba7c6cc","sha256:5f4cb0ee9a023f9608cdb662df7e14016d63d99c9f7559806a6cae642d1024dd"],"state_sha256":"f52e42678ee797a710fc656df7f8db88404e0e38cd963e7f2bcd2c27b44bc3c6"}