{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PUJJ54ZIHK25X6VG3DI7WS7ZL7","short_pith_number":"pith:PUJJ54ZI","schema_version":"1.0","canonical_sha256":"7d129ef3283ab5dbfaa6d8d1fb4bf95fea3835e889efeb0e6a1cbeb05e95b584","source":{"kind":"arxiv","id":"2410.03755","version":2},"attestation_state":"computed","paper":{"title":"Denoising with a Joint-Embedding Predictive Architecture","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dengsheng Chen, Enhua Wu, Jie Hu, Xiaoming Wei","submitted_at":"2024-10-02T05:57:10Z","abstract_excerpt":"Joint-embedding predictive architectures (JEPAs) have shown substantial promise in self-supervised representation learning, yet their application in generative modeling remains underexplored. Conversely, diffusion models have demonstrated significant efficacy in modeling arbitrary probability distributions. In this paper, we introduce Denoising with a Joint-Embedding Predictive Architecture (D-JEPA), pioneering the integration of JEPA within generative modeling. By recognizing JEPA as a form of masked image modeling, we reinterpret it as a generalized next-token prediction strategy, facilitati"},"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":"2410.03755","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T05:57:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f870a16e5312eae7bc3b671a6477552fcd190e43765789d13dcbcc2687fb8b74","abstract_canon_sha256":"27378deb52bae3fed6ecad34da25610dd62b6c88e13e1a0342f124a7585c39e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:09.887683Z","signature_b64":"RX1dYJ9PBNyyjyi5BMXqfqO5jWkLMGAPMmZGlanCqJ3Ir6euWMMx3UCA2HYS01HQ1tHPe37HiIEATI/tDIjJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d129ef3283ab5dbfaa6d8d1fb4bf95fea3835e889efeb0e6a1cbeb05e95b584","last_reissued_at":"2026-07-05T10:09:09.887192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:09.887192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Denoising with a Joint-Embedding Predictive Architecture","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dengsheng Chen, Enhua Wu, Jie Hu, Xiaoming Wei","submitted_at":"2024-10-02T05:57:10Z","abstract_excerpt":"Joint-embedding predictive architectures (JEPAs) have shown substantial promise in self-supervised representation learning, yet their application in generative modeling remains underexplored. Conversely, diffusion models have demonstrated significant efficacy in modeling arbitrary probability distributions. In this paper, we introduce Denoising with a Joint-Embedding Predictive Architecture (D-JEPA), pioneering the integration of JEPA within generative modeling. By recognizing JEPA as a form of masked image modeling, we reinterpret it as a generalized next-token prediction strategy, facilitati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03755","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/2410.03755/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":"2410.03755","created_at":"2026-07-05T10:09:09.887252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03755v2","created_at":"2026-07-05T10:09:09.887252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03755","created_at":"2026-07-05T10:09:09.887252+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUJJ54ZIHK25","created_at":"2026-07-05T10:09:09.887252+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUJJ54ZIHK25X6VG","created_at":"2026-07-05T10:09:09.887252+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUJJ54ZI","created_at":"2026-07-05T10:09:09.887252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13518","citing_title":"From Alignment to Prediction: A Study of Self-Supervised Learning and Predictive Representation Learning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUJJ54ZIHK25X6VG3DI7WS7ZL7","json":"https://pith.science/pith/PUJJ54ZIHK25X6VG3DI7WS7ZL7.json","graph_json":"https://pith.science/api/pith-number/PUJJ54ZIHK25X6VG3DI7WS7ZL7/graph.json","events_json":"https://pith.science/api/pith-number/PUJJ54ZIHK25X6VG3DI7WS7ZL7/events.json","paper":"https://pith.science/paper/PUJJ54ZI"},"agent_actions":{"view_html":"https://pith.science/pith/PUJJ54ZIHK25X6VG3DI7WS7ZL7","download_json":"https://pith.science/pith/PUJJ54ZIHK25X6VG3DI7WS7ZL7.json","view_paper":"https://pith.science/paper/PUJJ54ZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03755&json=true","fetch_graph":"https://pith.science/api/pith-number/PUJJ54ZIHK25X6VG3DI7WS7ZL7/graph.json","fetch_events":"https://pith.science/api/pith-number/PUJJ54ZIHK25X6VG3DI7WS7ZL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUJJ54ZIHK25X6VG3DI7WS7ZL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUJJ54ZIHK25X6VG3DI7WS7ZL7/action/storage_attestation","attest_author":"https://pith.science/pith/PUJJ54ZIHK25X6VG3DI7WS7ZL7/action/author_attestation","sign_citation":"https://pith.science/pith/PUJJ54ZIHK25X6VG3DI7WS7ZL7/action/citation_signature","submit_replication":"https://pith.science/pith/PUJJ54ZIHK25X6VG3DI7WS7ZL7/action/replication_record"}},"created_at":"2026-07-05T10:09:09.887252+00:00","updated_at":"2026-07-05T10:09:09.887252+00:00"}