{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VY4GX7OUNHWFM2LATCN4W7V3DC","short_pith_number":"pith:VY4GX7OU","schema_version":"1.0","canonical_sha256":"ae386bfdd469ec566960989bcb7ebb1886b0be6146d319bc9c647f11f08896a3","source":{"kind":"arxiv","id":"2304.03977","version":1},"attestation_state":"computed","paper":{"title":"EMP-SSL: Towards Self-Supervised Learning in One Training Epoch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Shengbang Tong, Yann LeCun, Yi Ma, Yubei Chen","submitted_at":"2023-04-08T10:09:30Z","abstract_excerpt":"Recently, self-supervised learning (SSL) has achieved tremendous success in learning image representation. Despite the empirical success, most self-supervised learning methods are rather \"inefficient\" learners, typically taking hundreds of training epochs to fully converge. In this work, we show that the key towards efficient self-supervised learning is to increase the number of crops from each image instance. Leveraging one of the state-of-the-art SSL method, we introduce a simplistic form of self-supervised learning method called Extreme-Multi-Patch Self-Supervised-Learning (EMP-SSL) that do"},"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":"2304.03977","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-08T10:09:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"605e36b1c01869a5e1eac01732843dab4daf351040a8b6c464eaf5a55ffbd191","abstract_canon_sha256":"4aa3be73b4480ef4e94626125df54f316e0bce14a50366c9875d8eec257cddae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:09.827348Z","signature_b64":"izdvJPngriJRUtJNVJq5pUJ3IUkRZYb44NQtCC3+qxzN5jNQFjgrJAGNj/0rqQCtgHUfmksOTb6UDpez+4A0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae386bfdd469ec566960989bcb7ebb1886b0be6146d319bc9c647f11f08896a3","last_reissued_at":"2026-07-05T05:59:09.826896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:09.826896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMP-SSL: Towards Self-Supervised Learning in One Training Epoch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Shengbang Tong, Yann LeCun, Yi Ma, Yubei Chen","submitted_at":"2023-04-08T10:09:30Z","abstract_excerpt":"Recently, self-supervised learning (SSL) has achieved tremendous success in learning image representation. Despite the empirical success, most self-supervised learning methods are rather \"inefficient\" learners, typically taking hundreds of training epochs to fully converge. In this work, we show that the key towards efficient self-supervised learning is to increase the number of crops from each image instance. Leveraging one of the state-of-the-art SSL method, we introduce a simplistic form of self-supervised learning method called Extreme-Multi-Patch Self-Supervised-Learning (EMP-SSL) that do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03977","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/2304.03977/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":"2304.03977","created_at":"2026-07-05T05:59:09.826956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03977v1","created_at":"2026-07-05T05:59:09.826956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03977","created_at":"2026-07-05T05:59:09.826956+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY4GX7OUNHWF","created_at":"2026-07-05T05:59:09.826956+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY4GX7OUNHWFM2LA","created_at":"2026-07-05T05:59:09.826956+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY4GX7OU","created_at":"2026-07-05T05:59:09.826956+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":144,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY4GX7OUNHWFM2LATCN4W7V3DC","json":"https://pith.science/pith/VY4GX7OUNHWFM2LATCN4W7V3DC.json","graph_json":"https://pith.science/api/pith-number/VY4GX7OUNHWFM2LATCN4W7V3DC/graph.json","events_json":"https://pith.science/api/pith-number/VY4GX7OUNHWFM2LATCN4W7V3DC/events.json","paper":"https://pith.science/paper/VY4GX7OU"},"agent_actions":{"view_html":"https://pith.science/pith/VY4GX7OUNHWFM2LATCN4W7V3DC","download_json":"https://pith.science/pith/VY4GX7OUNHWFM2LATCN4W7V3DC.json","view_paper":"https://pith.science/paper/VY4GX7OU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03977&json=true","fetch_graph":"https://pith.science/api/pith-number/VY4GX7OUNHWFM2LATCN4W7V3DC/graph.json","fetch_events":"https://pith.science/api/pith-number/VY4GX7OUNHWFM2LATCN4W7V3DC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY4GX7OUNHWFM2LATCN4W7V3DC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY4GX7OUNHWFM2LATCN4W7V3DC/action/storage_attestation","attest_author":"https://pith.science/pith/VY4GX7OUNHWFM2LATCN4W7V3DC/action/author_attestation","sign_citation":"https://pith.science/pith/VY4GX7OUNHWFM2LATCN4W7V3DC/action/citation_signature","submit_replication":"https://pith.science/pith/VY4GX7OUNHWFM2LATCN4W7V3DC/action/replication_record"}},"created_at":"2026-07-05T05:59:09.826956+00:00","updated_at":"2026-07-05T05:59:09.826956+00:00"}