{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OLVZJOSNABV7CUGELMYRXQMUOP","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":"c018ce86490d615c7e049cf30b2c60a1a063a9695618831ed642f95e2a98283d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T01:09:06Z","title_canon_sha256":"356d5ef9dc23048d8945f75355bc32b9b4281febac0813833cf2d0e8fdb28686"},"schema_version":"1.0","source":{"id":"2607.09024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09024","created_at":"2026-07-13T00:17:35Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09024v1","created_at":"2026-07-13T00:17:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09024","created_at":"2026-07-13T00:17:35Z"},{"alias_kind":"pith_short_12","alias_value":"OLVZJOSNABV7","created_at":"2026-07-13T00:17:35Z"},{"alias_kind":"pith_short_16","alias_value":"OLVZJOSNABV7CUGE","created_at":"2026-07-13T00:17:35Z"},{"alias_kind":"pith_short_8","alias_value":"OLVZJOSN","created_at":"2026-07-13T00:17:35Z"}],"graph_snapshots":[{"event_id":"sha256:f538c11af485c615a128faa443408cec3586683da93bd5ea95ed3ea8b832799c","target":"graph","created_at":"2026-07-13T00:17:35Z","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/2607.09024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models. What, then, is the equivalent catalyst needed to achieve a general-purpose model in computer vision? In this paper, we contend that large-scale text-to-video generation serves as a strong pre-training paradigm for computer vision, providing the necessary spatiotemporal priors, vision-language alignment, and scalability required for general visual intelligence. We introduce GenCeption, which leverages a pre-trained video generative diffusion backbone to define a feed-forward percep","authors_text":"Andrei Zanfir, Andrew Zisserman, Chuhan Zhang, Cristian Sminchisescu, Eduard Gabriel Bazavan, Jasper Uijlings, Joao Carreira, Kaiming He, Letian Wang, Misha Andriluka, Rishabh Kabra, Steven Waslander","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T01:09:06Z","title":"Video Generation Models are General-Purpose Vision Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09024","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":"sha256:207e87c36e84b10e3fd436f5d7e06906a528ea7008dd9964737deea731e2c277","target":"record","created_at":"2026-07-13T00:17:35Z","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":"c018ce86490d615c7e049cf30b2c60a1a063a9695618831ed642f95e2a98283d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T01:09:06Z","title_canon_sha256":"356d5ef9dc23048d8945f75355bc32b9b4281febac0813833cf2d0e8fdb28686"},"schema_version":"1.0","source":{"id":"2607.09024","kind":"arxiv","version":1}},"canonical_sha256":"72eb94ba4d006bf150c45b311bc19473d601a0372be0d8db47310594283a1205","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72eb94ba4d006bf150c45b311bc19473d601a0372be0d8db47310594283a1205","first_computed_at":"2026-07-13T00:17:35.149913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:35.149913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7wUTKFkrMDBf3wpoBqSRpFvDTLJvrQDuLhN7UAEIMIziNSziGZ4I1aSi2ONMmwcu8PeVhmM4uNZhaYV4D87BBQ==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:35.151464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:207e87c36e84b10e3fd436f5d7e06906a528ea7008dd9964737deea731e2c277","sha256:f538c11af485c615a128faa443408cec3586683da93bd5ea95ed3ea8b832799c"],"state_sha256":"9a3dbfc7f0aec6e8773215785b200f093feafd37b3ff0f47e6532af046e3cf8e"}