{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GYHNDF2EZRF65TU6TEI6LHSCZ3","short_pith_number":"pith:GYHNDF2E","schema_version":"1.0","canonical_sha256":"360ed19744cc4beece9e9911e59e42cec006b87c41ca663a8390ac801aa4e89e","source":{"kind":"arxiv","id":"2408.07514","version":2},"attestation_state":"computed","paper":{"title":"CNN-JEPA: Self-Supervised Pretraining Convolutional Neural Networks Using Joint Embedding Predictive Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andr\\'as Kalapos, B\\'alint Gyires-T\\'oth","submitted_at":"2024-08-14T12:48:37Z","abstract_excerpt":"Self-supervised learning (SSL) has become an important approach in pretraining large neural networks, enabling unprecedented scaling of model and dataset sizes. While recent advances like I-JEPA have shown promising results for Vision Transformers, adapting such methods to Convolutional Neural Networks (CNNs) presents unique challenges. In this paper, we introduce CNN-JEPA, a novel SSL method that successfully applies the joint embedding predictive architecture approach to CNNs. Our method incorporates a sparse CNN encoder to handle masked inputs, a fully convolutional predictor using depthwis"},"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":"2408.07514","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T12:48:37Z","cross_cats_sorted":[],"title_canon_sha256":"0424004c5c7c63b153862a94ac6e19c41b4868dc08eb313ad6c1cb5882160d14","abstract_canon_sha256":"99bebeb87da6870885f7c1ac1c39335faa7150439e1b753820fb5eb360573089"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:20.403051Z","signature_b64":"LNw/JKihVrCkKVegvOXUN1mUB3IjwlQ2yFGTcQxq85ssyMvfq04nlav92iG6JX+qaAv9C6XsAMUwUlWoEe7mBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360ed19744cc4beece9e9911e59e42cec006b87c41ca663a8390ac801aa4e89e","last_reissued_at":"2026-07-05T10:28:20.402458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:20.402458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CNN-JEPA: Self-Supervised Pretraining Convolutional Neural Networks Using Joint Embedding Predictive Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andr\\'as Kalapos, B\\'alint Gyires-T\\'oth","submitted_at":"2024-08-14T12:48:37Z","abstract_excerpt":"Self-supervised learning (SSL) has become an important approach in pretraining large neural networks, enabling unprecedented scaling of model and dataset sizes. While recent advances like I-JEPA have shown promising results for Vision Transformers, adapting such methods to Convolutional Neural Networks (CNNs) presents unique challenges. In this paper, we introduce CNN-JEPA, a novel SSL method that successfully applies the joint embedding predictive architecture approach to CNNs. Our method incorporates a sparse CNN encoder to handle masked inputs, a fully convolutional predictor using depthwis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07514","kind":"arxiv","version":2},"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/2408.07514/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":"2408.07514","created_at":"2026-07-05T10:28:20.402525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07514v2","created_at":"2026-07-05T10:28:20.402525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07514","created_at":"2026-07-05T10:28:20.402525+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYHNDF2EZRF6","created_at":"2026-07-05T10:28:20.402525+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYHNDF2EZRF65TU6","created_at":"2026-07-05T10:28:20.402525+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYHNDF2E","created_at":"2026-07-05T10:28:20.402525+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/GYHNDF2EZRF65TU6TEI6LHSCZ3","json":"https://pith.science/pith/GYHNDF2EZRF65TU6TEI6LHSCZ3.json","graph_json":"https://pith.science/api/pith-number/GYHNDF2EZRF65TU6TEI6LHSCZ3/graph.json","events_json":"https://pith.science/api/pith-number/GYHNDF2EZRF65TU6TEI6LHSCZ3/events.json","paper":"https://pith.science/paper/GYHNDF2E"},"agent_actions":{"view_html":"https://pith.science/pith/GYHNDF2EZRF65TU6TEI6LHSCZ3","download_json":"https://pith.science/pith/GYHNDF2EZRF65TU6TEI6LHSCZ3.json","view_paper":"https://pith.science/paper/GYHNDF2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07514&json=true","fetch_graph":"https://pith.science/api/pith-number/GYHNDF2EZRF65TU6TEI6LHSCZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/GYHNDF2EZRF65TU6TEI6LHSCZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYHNDF2EZRF65TU6TEI6LHSCZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYHNDF2EZRF65TU6TEI6LHSCZ3/action/storage_attestation","attest_author":"https://pith.science/pith/GYHNDF2EZRF65TU6TEI6LHSCZ3/action/author_attestation","sign_citation":"https://pith.science/pith/GYHNDF2EZRF65TU6TEI6LHSCZ3/action/citation_signature","submit_replication":"https://pith.science/pith/GYHNDF2EZRF65TU6TEI6LHSCZ3/action/replication_record"}},"created_at":"2026-07-05T10:28:20.402525+00:00","updated_at":"2026-07-05T10:28:20.402525+00:00"}