{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LRFUGFX3ZZYM6JYCJEJBDZDVNR","short_pith_number":"pith:LRFUGFX3","schema_version":"1.0","canonical_sha256":"5c4b4316fbce70cf2702491211e4756c52c8c144757e7ce11dd16be0e30d78b9","source":{"kind":"arxiv","id":"2504.16140","version":1},"attestation_state":"computed","paper":{"title":"SparseJEPA: Sparse Representation Learning of Joint Embedding Predictive Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lav Varshney, Max Hartman","submitted_at":"2025-04-22T02:43:00Z","abstract_excerpt":"Joint Embedding Predictive Architectures (JEPA) have emerged as a powerful framework for learning general-purpose representations. However, these models often lack interpretability and suffer from inefficiencies due to dense embedding representations. We propose SparseJEPA, an extension that integrates sparse representation learning into the JEPA framework to enhance the quality of learned representations. SparseJEPA employs a penalty method that encourages latent space variables to be shared among data features with strong semantic relationships, while maintaining predictive performance. We d"},"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":"2504.16140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T02:43:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f7eeb4d01a59356f192e070e54dd1d7f7f2071da3de03b0e42306dece9087c7","abstract_canon_sha256":"94f6e5bd17fb93dc94f5fea86412d52fd127b351315e619893e8215382896053"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:42.038746Z","signature_b64":"Ft2kQ9h5zL5V9jjIQtE/emLx4P2oynTCtC+W9R4drhnG4CBfw5gN8anOc7OZq0tzouLn+VXzr0KmwEbpuFFBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c4b4316fbce70cf2702491211e4756c52c8c144757e7ce11dd16be0e30d78b9","last_reissued_at":"2026-07-05T10:52:42.038273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:42.038273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SparseJEPA: Sparse Representation Learning of Joint Embedding Predictive Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lav Varshney, Max Hartman","submitted_at":"2025-04-22T02:43:00Z","abstract_excerpt":"Joint Embedding Predictive Architectures (JEPA) have emerged as a powerful framework for learning general-purpose representations. However, these models often lack interpretability and suffer from inefficiencies due to dense embedding representations. We propose SparseJEPA, an extension that integrates sparse representation learning into the JEPA framework to enhance the quality of learned representations. SparseJEPA employs a penalty method that encourages latent space variables to be shared among data features with strong semantic relationships, while maintaining predictive performance. We d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16140","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/2504.16140/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":"2504.16140","created_at":"2026-07-05T10:52:42.038343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16140v1","created_at":"2026-07-05T10:52:42.038343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16140","created_at":"2026-07-05T10:52:42.038343+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRFUGFX3ZZYM","created_at":"2026-07-05T10:52:42.038343+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRFUGFX3ZZYM6JYC","created_at":"2026-07-05T10:52:42.038343+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRFUGFX3","created_at":"2026-07-05T10:52:42.038343+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/LRFUGFX3ZZYM6JYCJEJBDZDVNR","json":"https://pith.science/pith/LRFUGFX3ZZYM6JYCJEJBDZDVNR.json","graph_json":"https://pith.science/api/pith-number/LRFUGFX3ZZYM6JYCJEJBDZDVNR/graph.json","events_json":"https://pith.science/api/pith-number/LRFUGFX3ZZYM6JYCJEJBDZDVNR/events.json","paper":"https://pith.science/paper/LRFUGFX3"},"agent_actions":{"view_html":"https://pith.science/pith/LRFUGFX3ZZYM6JYCJEJBDZDVNR","download_json":"https://pith.science/pith/LRFUGFX3ZZYM6JYCJEJBDZDVNR.json","view_paper":"https://pith.science/paper/LRFUGFX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16140&json=true","fetch_graph":"https://pith.science/api/pith-number/LRFUGFX3ZZYM6JYCJEJBDZDVNR/graph.json","fetch_events":"https://pith.science/api/pith-number/LRFUGFX3ZZYM6JYCJEJBDZDVNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRFUGFX3ZZYM6JYCJEJBDZDVNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRFUGFX3ZZYM6JYCJEJBDZDVNR/action/storage_attestation","attest_author":"https://pith.science/pith/LRFUGFX3ZZYM6JYCJEJBDZDVNR/action/author_attestation","sign_citation":"https://pith.science/pith/LRFUGFX3ZZYM6JYCJEJBDZDVNR/action/citation_signature","submit_replication":"https://pith.science/pith/LRFUGFX3ZZYM6JYCJEJBDZDVNR/action/replication_record"}},"created_at":"2026-07-05T10:52:42.038343+00:00","updated_at":"2026-07-05T10:52:42.038343+00:00"}