{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IJFTKYG2OMK22NKIIWEXR3SEG6","short_pith_number":"pith:IJFTKYG2","schema_version":"1.0","canonical_sha256":"424b3560da7315ad3548458978ee4437bc6ab8de0f1ab2534eb0e736a54e82ca","source":{"kind":"arxiv","id":"2412.10925","version":1},"attestation_state":"computed","paper":{"title":"Video Representation Learning with Joint-Embedding Predictive Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Katrina Drozdov, Ravid Shwartz-Ziv, Yann LeCun","submitted_at":"2024-12-14T18:33:29Z","abstract_excerpt":"Video representation learning is an increasingly important topic in machine learning research. We present Video JEPA with Variance-Covariance Regularization (VJ-VCR): a joint-embedding predictive architecture for self-supervised video representation learning that employs variance and covariance regularization to avoid representation collapse. We show that hidden representations from our VJ-VCR contain abstract, high-level information about the input data. Specifically, they outperform representations obtained from a generative baseline on downstream tasks that require understanding of the unde"},"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":"2412.10925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T18:33:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98d32c50e7f6d7fe47242a83a02c0ba61908d084ef537316a511d3691896ad14","abstract_canon_sha256":"fd5a0e627d515490fef884043877513937cac850f6aeb1e7defccec2c0c0d1b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:24.556746Z","signature_b64":"ar2Gy/QdyyLHv7/d5yquTmhsT4hsZnbaXBaCKdNeMBOebpyjNqAglMOOpGHJZ57xMRjSI5nJSsC/ip8OifIdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"424b3560da7315ad3548458978ee4437bc6ab8de0f1ab2534eb0e736a54e82ca","last_reissued_at":"2026-07-05T09:49:24.556231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:24.556231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Representation Learning with Joint-Embedding Predictive Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Katrina Drozdov, Ravid Shwartz-Ziv, Yann LeCun","submitted_at":"2024-12-14T18:33:29Z","abstract_excerpt":"Video representation learning is an increasingly important topic in machine learning research. We present Video JEPA with Variance-Covariance Regularization (VJ-VCR): a joint-embedding predictive architecture for self-supervised video representation learning that employs variance and covariance regularization to avoid representation collapse. We show that hidden representations from our VJ-VCR contain abstract, high-level information about the input data. Specifically, they outperform representations obtained from a generative baseline on downstream tasks that require understanding of the unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10925","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/2412.10925/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":"2412.10925","created_at":"2026-07-05T09:49:24.556300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10925v1","created_at":"2026-07-05T09:49:24.556300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10925","created_at":"2026-07-05T09:49:24.556300+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJFTKYG2OMK2","created_at":"2026-07-05T09:49:24.556300+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJFTKYG2OMK22NKI","created_at":"2026-07-05T09:49:24.556300+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJFTKYG2","created_at":"2026-07-05T09:49:24.556300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26410","citing_title":"Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05586","citing_title":"AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJFTKYG2OMK22NKIIWEXR3SEG6","json":"https://pith.science/pith/IJFTKYG2OMK22NKIIWEXR3SEG6.json","graph_json":"https://pith.science/api/pith-number/IJFTKYG2OMK22NKIIWEXR3SEG6/graph.json","events_json":"https://pith.science/api/pith-number/IJFTKYG2OMK22NKIIWEXR3SEG6/events.json","paper":"https://pith.science/paper/IJFTKYG2"},"agent_actions":{"view_html":"https://pith.science/pith/IJFTKYG2OMK22NKIIWEXR3SEG6","download_json":"https://pith.science/pith/IJFTKYG2OMK22NKIIWEXR3SEG6.json","view_paper":"https://pith.science/paper/IJFTKYG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10925&json=true","fetch_graph":"https://pith.science/api/pith-number/IJFTKYG2OMK22NKIIWEXR3SEG6/graph.json","fetch_events":"https://pith.science/api/pith-number/IJFTKYG2OMK22NKIIWEXR3SEG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJFTKYG2OMK22NKIIWEXR3SEG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJFTKYG2OMK22NKIIWEXR3SEG6/action/storage_attestation","attest_author":"https://pith.science/pith/IJFTKYG2OMK22NKIIWEXR3SEG6/action/author_attestation","sign_citation":"https://pith.science/pith/IJFTKYG2OMK22NKIIWEXR3SEG6/action/citation_signature","submit_replication":"https://pith.science/pith/IJFTKYG2OMK22NKIIWEXR3SEG6/action/replication_record"}},"created_at":"2026-07-05T09:49:24.556300+00:00","updated_at":"2026-07-05T09:49:24.556300+00:00"}