{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JQ2QRNIDP4XFKFMIRQJ57SCX5I","short_pith_number":"pith:JQ2QRNID","schema_version":"1.0","canonical_sha256":"4c3508b5037f2e5515888c13dfc857ea0e128b97ae586c795ff683d9c98bda24","source":{"kind":"arxiv","id":"2303.01986","version":1},"attestation_state":"computed","paper":{"title":"Towards Democratizing Joint-Embedding Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Florian Bordes, Pascal Vincent, Randall Balestriero","submitted_at":"2023-03-03T14:55:44Z","abstract_excerpt":"Joint Embedding Self-Supervised Learning (JE-SSL) has seen rapid developments in recent years, due to its promise to effectively leverage large unlabeled data. The development of JE-SSL methods was driven primarily by the search for ever increasing downstream classification accuracies, using huge computational resources, and typically built upon insights and intuitions inherited from a close parent JE-SSL method. This has led unwittingly to numerous pre-conceived ideas that carried over across methods e.g. that SimCLR requires very large mini batches to yield competitive accuracies; that stron"},"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":"2303.01986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T14:55:44Z","cross_cats_sorted":[],"title_canon_sha256":"2e2183d591807a9ecbe018ebad47fc769edf2f8fd4a3cc1a5f96d42ef0a2b657","abstract_canon_sha256":"82e5f990805e28db67d9f2fe8ef0458d37e23a7b695871e4d755c64885df510a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:51.265192Z","signature_b64":"wP8QmCBPFGmmzimvcFGajsJkA/cWE+KOR+J1Zd4XrkdNtEsN4r57zbZBpkqOQaFBgAWRfs8U1ub59N8XSK5HCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c3508b5037f2e5515888c13dfc857ea0e128b97ae586c795ff683d9c98bda24","last_reissued_at":"2026-07-05T05:47:51.264764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:51.264764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Democratizing Joint-Embedding Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Florian Bordes, Pascal Vincent, Randall Balestriero","submitted_at":"2023-03-03T14:55:44Z","abstract_excerpt":"Joint Embedding Self-Supervised Learning (JE-SSL) has seen rapid developments in recent years, due to its promise to effectively leverage large unlabeled data. The development of JE-SSL methods was driven primarily by the search for ever increasing downstream classification accuracies, using huge computational resources, and typically built upon insights and intuitions inherited from a close parent JE-SSL method. This has led unwittingly to numerous pre-conceived ideas that carried over across methods e.g. that SimCLR requires very large mini batches to yield competitive accuracies; that stron"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01986","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/2303.01986/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":"2303.01986","created_at":"2026-07-05T05:47:51.264834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.01986v1","created_at":"2026-07-05T05:47:51.264834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01986","created_at":"2026-07-05T05:47:51.264834+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQ2QRNIDP4XF","created_at":"2026-07-05T05:47:51.264834+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQ2QRNIDP4XFKFMI","created_at":"2026-07-05T05:47:51.264834+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQ2QRNID","created_at":"2026-07-05T05:47:51.264834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11170","citing_title":"Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17454","citing_title":"HSG: Hyperbolic Scene Graph","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQ2QRNIDP4XFKFMIRQJ57SCX5I","json":"https://pith.science/pith/JQ2QRNIDP4XFKFMIRQJ57SCX5I.json","graph_json":"https://pith.science/api/pith-number/JQ2QRNIDP4XFKFMIRQJ57SCX5I/graph.json","events_json":"https://pith.science/api/pith-number/JQ2QRNIDP4XFKFMIRQJ57SCX5I/events.json","paper":"https://pith.science/paper/JQ2QRNID"},"agent_actions":{"view_html":"https://pith.science/pith/JQ2QRNIDP4XFKFMIRQJ57SCX5I","download_json":"https://pith.science/pith/JQ2QRNIDP4XFKFMIRQJ57SCX5I.json","view_paper":"https://pith.science/paper/JQ2QRNID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.01986&json=true","fetch_graph":"https://pith.science/api/pith-number/JQ2QRNIDP4XFKFMIRQJ57SCX5I/graph.json","fetch_events":"https://pith.science/api/pith-number/JQ2QRNIDP4XFKFMIRQJ57SCX5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQ2QRNIDP4XFKFMIRQJ57SCX5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQ2QRNIDP4XFKFMIRQJ57SCX5I/action/storage_attestation","attest_author":"https://pith.science/pith/JQ2QRNIDP4XFKFMIRQJ57SCX5I/action/author_attestation","sign_citation":"https://pith.science/pith/JQ2QRNIDP4XFKFMIRQJ57SCX5I/action/citation_signature","submit_replication":"https://pith.science/pith/JQ2QRNIDP4XFKFMIRQJ57SCX5I/action/replication_record"}},"created_at":"2026-07-05T05:47:51.264834+00:00","updated_at":"2026-07-05T05:47:51.264834+00:00"}