{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YYUNF4CX555R3JSJZWFUQFAX6D","short_pith_number":"pith:YYUNF4CX","schema_version":"1.0","canonical_sha256":"c628d2f057ef7b1da649cd8b481417f0cd8c93f3d62cda2521d350ab957f3162","source":{"kind":"arxiv","id":"2608.04213","version":1},"attestation_state":"computed","paper":{"title":"Attention-Only White-Box Transformer via LeJEPA-Based Self-Supervised Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Yan, Haoyang Jiang, Libin Hou, Linyuan Wang, Nuolin Sun, Yang Bai","submitted_at":"2026-08-04T20:26:12Z","abstract_excerpt":"Existing studies on self-supervised learning for white-box networks typically decouple the derivation of white-box networks via optimization algorithms from self-supervised learning paradigms. In this work, we instead revisit the two components from a joint perspective. The LeJEPA-based self-supervised framework assumes an isotropic Gaussian distribution as the optimal embedding distribution for downstream tasks, which is conceptually equivalent to the expansion term $R(Z)$ in the sparse rate reduction objective guiding white-box Transformer optimization. Building on this observation, we use t"},"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":"2608.04213","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T20:26:12Z","cross_cats_sorted":[],"title_canon_sha256":"a5aea092d2287753df7d96dcb3d28b28fa4663bfe410c8ce6191c2dd10212f2c","abstract_canon_sha256":"adf03c47808af777fcb872b2b886afe3c0404aaa873cb930d1b0d87ecba7b274"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:31:41.177944Z","signature_b64":"qVx+tPeHZ460ZX8khH92me6ckmmO+A1lA1G7Pk29xWHBbT/aMNQN4LBtUUui9KSB9E+p5NGrUYSp0IDYSWaFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c628d2f057ef7b1da649cd8b481417f0cd8c93f3d62cda2521d350ab957f3162","last_reissued_at":"2026-08-06T01:31:41.176304Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:31:41.176304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-Only White-Box Transformer via LeJEPA-Based Self-Supervised Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Yan, Haoyang Jiang, Libin Hou, Linyuan Wang, Nuolin Sun, Yang Bai","submitted_at":"2026-08-04T20:26:12Z","abstract_excerpt":"Existing studies on self-supervised learning for white-box networks typically decouple the derivation of white-box networks via optimization algorithms from self-supervised learning paradigms. In this work, we instead revisit the two components from a joint perspective. The LeJEPA-based self-supervised framework assumes an isotropic Gaussian distribution as the optimal embedding distribution for downstream tasks, which is conceptually equivalent to the expansion term $R(Z)$ in the sparse rate reduction objective guiding white-box Transformer optimization. Building on this observation, we use t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04213","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/2608.04213/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":"2608.04213","created_at":"2026-08-06T01:31:41.178203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04213v1","created_at":"2026-08-06T01:31:41.178203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04213","created_at":"2026-08-06T01:31:41.178203+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYUNF4CX555R","created_at":"2026-08-06T01:31:41.178203+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYUNF4CX555R3JSJ","created_at":"2026-08-06T01:31:41.178203+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYUNF4CX","created_at":"2026-08-06T01:31:41.178203+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/YYUNF4CX555R3JSJZWFUQFAX6D","json":"https://pith.science/pith/YYUNF4CX555R3JSJZWFUQFAX6D.json","graph_json":"https://pith.science/api/pith-number/YYUNF4CX555R3JSJZWFUQFAX6D/graph.json","events_json":"https://pith.science/api/pith-number/YYUNF4CX555R3JSJZWFUQFAX6D/events.json","paper":"https://pith.science/paper/YYUNF4CX"},"agent_actions":{"view_html":"https://pith.science/pith/YYUNF4CX555R3JSJZWFUQFAX6D","download_json":"https://pith.science/pith/YYUNF4CX555R3JSJZWFUQFAX6D.json","view_paper":"https://pith.science/paper/YYUNF4CX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04213&json=true","fetch_graph":"https://pith.science/api/pith-number/YYUNF4CX555R3JSJZWFUQFAX6D/graph.json","fetch_events":"https://pith.science/api/pith-number/YYUNF4CX555R3JSJZWFUQFAX6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYUNF4CX555R3JSJZWFUQFAX6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYUNF4CX555R3JSJZWFUQFAX6D/action/storage_attestation","attest_author":"https://pith.science/pith/YYUNF4CX555R3JSJZWFUQFAX6D/action/author_attestation","sign_citation":"https://pith.science/pith/YYUNF4CX555R3JSJZWFUQFAX6D/action/citation_signature","submit_replication":"https://pith.science/pith/YYUNF4CX555R3JSJZWFUQFAX6D/action/replication_record"}},"created_at":"2026-08-06T01:31:41.178203+00:00","updated_at":"2026-08-06T01:31:41.178203+00:00"}