{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UWKJ7EHVDZNMB6AQDAOUNWWSVN","short_pith_number":"pith:UWKJ7EHV","schema_version":"1.0","canonical_sha256":"a5949f90f51e5ac0f810181d46dad2ab482a3c3cc9370f271ef1a7de513ecc65","source":{"kind":"arxiv","id":"2605.17671","version":1},"attestation_state":"computed","paper":{"title":"PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Basile Terver, Jean Ponce, Michael Arbel","submitted_at":"2026-05-17T22:04:01Z","abstract_excerpt":"Non-contrastive self-supervised learning (SSL) is an effective framework for predictive representation learning, but popular (and in practice effective) methods such as SimSiam, BYOL, I-JEPA or DINO, which rely on a form of self-distillation to train a teacher-student network, remain poorly understood as they typically do not minimize a well-defined objective. We analyze the dynamics of a variant of the Joint Embedding Predictive Architecture (JEPA) using a regularized linear regressor to predict the learned representations of two views of the data from one another, and fully characterize its "},"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":"2605.17671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T22:04:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6ee5420c746c48750a7420f814e978ff862470f8875fbff14f32a0c9197c83c","abstract_canon_sha256":"028f596180a8449ce71f9c36877c6c7b226d8107006c48d3a43e8a6aedf7bfb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:51.925121Z","signature_b64":"ivuDT7BIGgSnoqyc2imuxmRs7GH/c2qNn0vHHF7G7i8KFQbUGY3CjYEkgDFXY87OzsO4fs1QpwOm4jcX1gl4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5949f90f51e5ac0f810181d46dad2ab482a3c3cc9370f271ef1a7de513ecc65","last_reissued_at":"2026-05-20T00:04:51.924293Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:51.924293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PEIRA: Learning Predictive Encoders through Inter-View Regressor Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Basile Terver, Jean Ponce, Michael Arbel","submitted_at":"2026-05-17T22:04:01Z","abstract_excerpt":"Non-contrastive self-supervised learning (SSL) is an effective framework for predictive representation learning, but popular (and in practice effective) methods such as SimSiam, BYOL, I-JEPA or DINO, which rely on a form of self-distillation to train a teacher-student network, remain poorly understood as they typically do not minimize a well-defined objective. We analyze the dynamics of a variant of the Joint Embedding Predictive Architecture (JEPA) using a regularized linear regressor to predict the learned representations of two views of the data from one another, and fully characterize its "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17671","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/2605.17671/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T21:51:59.695214Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:44.263052Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.534526Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.449306Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"798e6918927dc6d3eb9763dfc8310b615bf969566e6b2593638ec8cd4838ab6e"},"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":"2605.17671","created_at":"2026-05-20T00:04:51.924442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17671v1","created_at":"2026-05-20T00:04:51.924442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17671","created_at":"2026-05-20T00:04:51.924442+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWKJ7EHVDZNM","created_at":"2026-05-20T00:04:51.924442+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWKJ7EHVDZNMB6AQ","created_at":"2026-05-20T00:04:51.924442+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWKJ7EHV","created_at":"2026-05-20T00:04:51.924442+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/UWKJ7EHVDZNMB6AQDAOUNWWSVN","json":"https://pith.science/pith/UWKJ7EHVDZNMB6AQDAOUNWWSVN.json","graph_json":"https://pith.science/api/pith-number/UWKJ7EHVDZNMB6AQDAOUNWWSVN/graph.json","events_json":"https://pith.science/api/pith-number/UWKJ7EHVDZNMB6AQDAOUNWWSVN/events.json","paper":"https://pith.science/paper/UWKJ7EHV"},"agent_actions":{"view_html":"https://pith.science/pith/UWKJ7EHVDZNMB6AQDAOUNWWSVN","download_json":"https://pith.science/pith/UWKJ7EHVDZNMB6AQDAOUNWWSVN.json","view_paper":"https://pith.science/paper/UWKJ7EHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17671&json=true","fetch_graph":"https://pith.science/api/pith-number/UWKJ7EHVDZNMB6AQDAOUNWWSVN/graph.json","fetch_events":"https://pith.science/api/pith-number/UWKJ7EHVDZNMB6AQDAOUNWWSVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWKJ7EHVDZNMB6AQDAOUNWWSVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWKJ7EHVDZNMB6AQDAOUNWWSVN/action/storage_attestation","attest_author":"https://pith.science/pith/UWKJ7EHVDZNMB6AQDAOUNWWSVN/action/author_attestation","sign_citation":"https://pith.science/pith/UWKJ7EHVDZNMB6AQDAOUNWWSVN/action/citation_signature","submit_replication":"https://pith.science/pith/UWKJ7EHVDZNMB6AQDAOUNWWSVN/action/replication_record"}},"created_at":"2026-05-20T00:04:51.924442+00:00","updated_at":"2026-05-20T00:04:51.924442+00:00"}