{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJ5PFVPQJFX43VXUXJ7UT5LXEX","short_pith_number":"pith:JJ5PFVPQ","schema_version":"1.0","canonical_sha256":"4a7af2d5f0496fcdd6f4ba7f49f57725d59ab175a6f55646f443c38f0cc90421","source":{"kind":"arxiv","id":"2606.02572","version":1},"attestation_state":"computed","paper":{"title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyu Wu, Morgan Levine, Randall Balestriero","submitted_at":"2026-06-01T17:58:01Z","abstract_excerpt":"Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit regularization of the embedding space. Among the latter, VICReg decomposes regularization into variance and covariance objectives, offering flexibility and interpretability. However, covariance captures only second-order statistics -- encouraging decorrelation but failing to enforce the full distributional shape needed for stable training. Sketching-based methods such as SIGReg address this by aligning embeddings to an isotropic Gaussian, but lack flexibility and suffer from vanishing gradients 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":"2606.02572","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T17:58:01Z","cross_cats_sorted":[],"title_canon_sha256":"be5622781bcba98804588a5f1e342d2497dca063a422d9061d69c92ecb63174b","abstract_canon_sha256":"aadadc0b3452fa872bf12271dc7b9fa692245ecb388cc83e27fa0017c0c6f087"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:05:10.489997Z","signature_b64":"WH+rFCDgpo82+Z69bCJaRASm4CZ9b32g+7K/OqMjL7z9jLZ2UU0zxuBFsK6imE3APAYYItvrnKQU/QHO//XDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a7af2d5f0496fcdd6f4ba7f49f57725d59ab175a6f55646f443c38f0cc90421","last_reissued_at":"2026-06-02T03:05:10.489643Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:05:10.489643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISReg: Variance-Invariance-Sketching Regularization for JEPA training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyu Wu, Morgan Levine, Randall Balestriero","submitted_at":"2026-06-01T17:58:01Z","abstract_excerpt":"Self-supervised learning methods prevent embedding collapse via modeling heuristics or explicit regularization of the embedding space. Among the latter, VICReg decomposes regularization into variance and covariance objectives, offering flexibility and interpretability. However, covariance captures only second-order statistics -- encouraging decorrelation but failing to enforce the full distributional shape needed for stable training. Sketching-based methods such as SIGReg address this by aligning embeddings to an isotropic Gaussian, but lack flexibility and suffer from vanishing gradients unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02572","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/2606.02572/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":"2606.02572","created_at":"2026-06-02T03:05:10.489698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02572v1","created_at":"2026-06-02T03:05:10.489698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02572","created_at":"2026-06-02T03:05:10.489698+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJ5PFVPQJFX4","created_at":"2026-06-02T03:05:10.489698+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJ5PFVPQJFX43VXU","created_at":"2026-06-02T03:05:10.489698+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJ5PFVPQ","created_at":"2026-06-02T03:05:10.489698+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/JJ5PFVPQJFX43VXUXJ7UT5LXEX","json":"https://pith.science/pith/JJ5PFVPQJFX43VXUXJ7UT5LXEX.json","graph_json":"https://pith.science/api/pith-number/JJ5PFVPQJFX43VXUXJ7UT5LXEX/graph.json","events_json":"https://pith.science/api/pith-number/JJ5PFVPQJFX43VXUXJ7UT5LXEX/events.json","paper":"https://pith.science/paper/JJ5PFVPQ"},"agent_actions":{"view_html":"https://pith.science/pith/JJ5PFVPQJFX43VXUXJ7UT5LXEX","download_json":"https://pith.science/pith/JJ5PFVPQJFX43VXUXJ7UT5LXEX.json","view_paper":"https://pith.science/paper/JJ5PFVPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02572&json=true","fetch_graph":"https://pith.science/api/pith-number/JJ5PFVPQJFX43VXUXJ7UT5LXEX/graph.json","fetch_events":"https://pith.science/api/pith-number/JJ5PFVPQJFX43VXUXJ7UT5LXEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJ5PFVPQJFX43VXUXJ7UT5LXEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJ5PFVPQJFX43VXUXJ7UT5LXEX/action/storage_attestation","attest_author":"https://pith.science/pith/JJ5PFVPQJFX43VXUXJ7UT5LXEX/action/author_attestation","sign_citation":"https://pith.science/pith/JJ5PFVPQJFX43VXUXJ7UT5LXEX/action/citation_signature","submit_replication":"https://pith.science/pith/JJ5PFVPQJFX43VXUXJ7UT5LXEX/action/replication_record"}},"created_at":"2026-06-02T03:05:10.489698+00:00","updated_at":"2026-06-02T03:05:10.489698+00:00"}