{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OLVZJOSNABV7CUGELMYRXQMUOP","short_pith_number":"pith:OLVZJOSN","schema_version":"1.0","canonical_sha256":"72eb94ba4d006bf150c45b311bc19473d601a0372be0d8db47310594283a1205","source":{"kind":"arxiv","id":"2607.09024","version":1},"attestation_state":"computed","paper":{"title":"Video Generation Models are General-Purpose Vision Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2026-07-10T01:09:06Z","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"},"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":"2607.09024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T01:09:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"356d5ef9dc23048d8945f75355bc32b9b4281febac0813833cf2d0e8fdb28686","abstract_canon_sha256":"c018ce86490d615c7e049cf30b2c60a1a063a9695618831ed642f95e2a98283d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:35.151464Z","signature_b64":"7wUTKFkrMDBf3wpoBqSRpFvDTLJvrQDuLhN7UAEIMIziNSziGZ4I1aSi2ONMmwcu8PeVhmM4uNZhaYV4D87BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72eb94ba4d006bf150c45b311bc19473d601a0372be0d8db47310594283a1205","last_reissued_at":"2026-07-13T00:17:35.149913Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:35.149913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Generation Models are General-Purpose Vision Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","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","submitted_at":"2026-07-10T01:09:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09024","kind":"arxiv","version":1},"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/2607.09024/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":"2607.09024","created_at":"2026-07-13T00:17:35.150759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09024v1","created_at":"2026-07-13T00:17:35.150759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09024","created_at":"2026-07-13T00:17:35.150759+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLVZJOSNABV7","created_at":"2026-07-13T00:17:35.150759+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLVZJOSNABV7CUGE","created_at":"2026-07-13T00:17:35.150759+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLVZJOSN","created_at":"2026-07-13T00:17:35.150759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLVZJOSNABV7CUGELMYRXQMUOP","json":"https://pith.science/pith/OLVZJOSNABV7CUGELMYRXQMUOP.json","graph_json":"https://pith.science/api/pith-number/OLVZJOSNABV7CUGELMYRXQMUOP/graph.json","events_json":"https://pith.science/api/pith-number/OLVZJOSNABV7CUGELMYRXQMUOP/events.json","paper":"https://pith.science/paper/OLVZJOSN"},"agent_actions":{"view_html":"https://pith.science/pith/OLVZJOSNABV7CUGELMYRXQMUOP","download_json":"https://pith.science/pith/OLVZJOSNABV7CUGELMYRXQMUOP.json","view_paper":"https://pith.science/paper/OLVZJOSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09024&json=true","fetch_graph":"https://pith.science/api/pith-number/OLVZJOSNABV7CUGELMYRXQMUOP/graph.json","fetch_events":"https://pith.science/api/pith-number/OLVZJOSNABV7CUGELMYRXQMUOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLVZJOSNABV7CUGELMYRXQMUOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLVZJOSNABV7CUGELMYRXQMUOP/action/storage_attestation","attest_author":"https://pith.science/pith/OLVZJOSNABV7CUGELMYRXQMUOP/action/author_attestation","sign_citation":"https://pith.science/pith/OLVZJOSNABV7CUGELMYRXQMUOP/action/citation_signature","submit_replication":"https://pith.science/pith/OLVZJOSNABV7CUGELMYRXQMUOP/action/replication_record"}},"created_at":"2026-07-13T00:17:35.150759+00:00","updated_at":"2026-07-13T00:17:35.150759+00:00"}