{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7TL6ZIVXDOYV75KSFGL3FEFJWR","short_pith_number":"pith:7TL6ZIVX","schema_version":"1.0","canonical_sha256":"fcd7eca2b71bb15ff5522997b290a9b45679af555e6dc9b75377c4d4eba0a7d9","source":{"kind":"arxiv","id":"2606.17603","version":1},"attestation_state":"computed","paper":{"title":"Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"ATT), Enric Meinhardt-Llopis (CB), Gabriele Facciolo (CB), IFUMI), L\\'eo Nicollier (CB, Marc Pic (ATT), Max Dunitz (ATT), Pablo Mus\\'e (CB","submitted_at":"2026-06-16T07:10:05Z","abstract_excerpt":"In Self-Supervised Learning (SSL), preventing representation collapse by explicitly enforcing a uniform distribution on the unit hypersphere has proven to be effective. However, current frameworks typically rely on sliced statistical regularizers such as SIGReg (used in LeJEPA) and SUSReg (used in SPHERE-JEPA), which approximate this continuous objective via Monte Carlo sampling along random 1D directions. This stochasticity injects projection variance into the training gradients, destabilizing optimization, and hindering convergence. In this work, we first show that analytically integrating o"},"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":"2606.17603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T07:10:05Z","cross_cats_sorted":[],"title_canon_sha256":"cda56b5c9be2989944d60dbdf83e07237e72854106bdfa8b7dc56e1e1dd026f3","abstract_canon_sha256":"2854d0d7996825de8e614b112f7f2474a231bf4c82ee2d662a16d5e70d806679"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:17.079103Z","signature_b64":"gDRBUMInd6BZ+LSJ00eZzoXAGNtBM16PlCMMZrAltp8hymflFiIrgxVm0DJ8KFBtaADUCHe0zoJQn/HscW+gBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcd7eca2b71bb15ff5522997b290a9b45679af555e6dc9b75377c4d4eba0a7d9","last_reissued_at":"2026-06-19T16:10:17.078769Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:17.078769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"ATT), Enric Meinhardt-Llopis (CB), Gabriele Facciolo (CB), IFUMI), L\\'eo Nicollier (CB, Marc Pic (ATT), Max Dunitz (ATT), Pablo Mus\\'e (CB","submitted_at":"2026-06-16T07:10:05Z","abstract_excerpt":"In Self-Supervised Learning (SSL), preventing representation collapse by explicitly enforcing a uniform distribution on the unit hypersphere has proven to be effective. However, current frameworks typically rely on sliced statistical regularizers such as SIGReg (used in LeJEPA) and SUSReg (used in SPHERE-JEPA), which approximate this continuous objective via Monte Carlo sampling along random 1D directions. This stochasticity injects projection variance into the training gradients, destabilizing optimization, and hindering convergence. In this work, we first show that analytically integrating o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17603","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/2606.17603/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":"2606.17603","created_at":"2026-06-19T16:10:17.078828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17603v1","created_at":"2026-06-19T16:10:17.078828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17603","created_at":"2026-06-19T16:10:17.078828+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TL6ZIVXDOYV","created_at":"2026-06-19T16:10:17.078828+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TL6ZIVXDOYV75KS","created_at":"2026-06-19T16:10:17.078828+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TL6ZIVX","created_at":"2026-06-19T16:10:17.078828+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/7TL6ZIVXDOYV75KSFGL3FEFJWR","json":"https://pith.science/pith/7TL6ZIVXDOYV75KSFGL3FEFJWR.json","graph_json":"https://pith.science/api/pith-number/7TL6ZIVXDOYV75KSFGL3FEFJWR/graph.json","events_json":"https://pith.science/api/pith-number/7TL6ZIVXDOYV75KSFGL3FEFJWR/events.json","paper":"https://pith.science/paper/7TL6ZIVX"},"agent_actions":{"view_html":"https://pith.science/pith/7TL6ZIVXDOYV75KSFGL3FEFJWR","download_json":"https://pith.science/pith/7TL6ZIVXDOYV75KSFGL3FEFJWR.json","view_paper":"https://pith.science/paper/7TL6ZIVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17603&json=true","fetch_graph":"https://pith.science/api/pith-number/7TL6ZIVXDOYV75KSFGL3FEFJWR/graph.json","fetch_events":"https://pith.science/api/pith-number/7TL6ZIVXDOYV75KSFGL3FEFJWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TL6ZIVXDOYV75KSFGL3FEFJWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TL6ZIVXDOYV75KSFGL3FEFJWR/action/storage_attestation","attest_author":"https://pith.science/pith/7TL6ZIVXDOYV75KSFGL3FEFJWR/action/author_attestation","sign_citation":"https://pith.science/pith/7TL6ZIVXDOYV75KSFGL3FEFJWR/action/citation_signature","submit_replication":"https://pith.science/pith/7TL6ZIVXDOYV75KSFGL3FEFJWR/action/replication_record"}},"created_at":"2026-06-19T16:10:17.078828+00:00","updated_at":"2026-06-19T16:10:17.078828+00:00"}