{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VQFDN5DZF535C4ELMMA56GLKAF","short_pith_number":"pith:VQFDN5DZ","schema_version":"1.0","canonical_sha256":"ac0a36f4792f77d1708b6301df196a0144817f94191044847671b49a48443b14","source":{"kind":"arxiv","id":"2501.03507","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Study of Accuracy-Robustness Tradeoff and Training Efficiency in Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fatemeh Ghofrani, Pooyan Jamshidi","submitted_at":"2025-01-07T03:50:11Z","abstract_excerpt":"Self-supervised learning (SSL) has significantly advanced image representation learning, yet efficiency challenges persist, particularly with adversarial training. Many SSL methods require extensive epochs to achieve convergence, a demand further amplified in adversarial settings. To address this inefficiency, we revisit the robust EMP-SSL framework, emphasizing the importance of increasing the number of crops per image to accelerate learning. Unlike traditional contrastive learning, robust EMP-SSL leverages multi-crop sampling, integrates an invariance term and regularization, and reduces tra"},"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":"2501.03507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T03:50:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a71f7b7cadf696090323da1f0cbc004cf8e2068dfe50a1d2ef6ebd5879fd0a04","abstract_canon_sha256":"38743fffbbcd80e049128d0eb8239278f444a4f15cc0f5b72840ffc0ab891946"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:55.792484Z","signature_b64":"OgDcaCYMFfgbFHWS4wo7llu+bgHy9D5TVAHWmeY2NUi99tbCBdakRbaFn9YNisapu3FLfKsrFcaDhFmQ/S13DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac0a36f4792f77d1708b6301df196a0144817f94191044847671b49a48443b14","last_reissued_at":"2026-07-05T09:57:55.792072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:55.792072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study of Accuracy-Robustness Tradeoff and Training Efficiency in Self-Supervised Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fatemeh Ghofrani, Pooyan Jamshidi","submitted_at":"2025-01-07T03:50:11Z","abstract_excerpt":"Self-supervised learning (SSL) has significantly advanced image representation learning, yet efficiency challenges persist, particularly with adversarial training. Many SSL methods require extensive epochs to achieve convergence, a demand further amplified in adversarial settings. To address this inefficiency, we revisit the robust EMP-SSL framework, emphasizing the importance of increasing the number of crops per image to accelerate learning. Unlike traditional contrastive learning, robust EMP-SSL leverages multi-crop sampling, integrates an invariance term and regularization, and reduces tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03507","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/2501.03507/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":"2501.03507","created_at":"2026-07-05T09:57:55.792125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03507v1","created_at":"2026-07-05T09:57:55.792125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03507","created_at":"2026-07-05T09:57:55.792125+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQFDN5DZF535","created_at":"2026-07-05T09:57:55.792125+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQFDN5DZF535C4EL","created_at":"2026-07-05T09:57:55.792125+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQFDN5DZ","created_at":"2026-07-05T09:57:55.792125+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/VQFDN5DZF535C4ELMMA56GLKAF","json":"https://pith.science/pith/VQFDN5DZF535C4ELMMA56GLKAF.json","graph_json":"https://pith.science/api/pith-number/VQFDN5DZF535C4ELMMA56GLKAF/graph.json","events_json":"https://pith.science/api/pith-number/VQFDN5DZF535C4ELMMA56GLKAF/events.json","paper":"https://pith.science/paper/VQFDN5DZ"},"agent_actions":{"view_html":"https://pith.science/pith/VQFDN5DZF535C4ELMMA56GLKAF","download_json":"https://pith.science/pith/VQFDN5DZF535C4ELMMA56GLKAF.json","view_paper":"https://pith.science/paper/VQFDN5DZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03507&json=true","fetch_graph":"https://pith.science/api/pith-number/VQFDN5DZF535C4ELMMA56GLKAF/graph.json","fetch_events":"https://pith.science/api/pith-number/VQFDN5DZF535C4ELMMA56GLKAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQFDN5DZF535C4ELMMA56GLKAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQFDN5DZF535C4ELMMA56GLKAF/action/storage_attestation","attest_author":"https://pith.science/pith/VQFDN5DZF535C4ELMMA56GLKAF/action/author_attestation","sign_citation":"https://pith.science/pith/VQFDN5DZF535C4ELMMA56GLKAF/action/citation_signature","submit_replication":"https://pith.science/pith/VQFDN5DZF535C4ELMMA56GLKAF/action/replication_record"}},"created_at":"2026-07-05T09:57:55.792125+00:00","updated_at":"2026-07-05T09:57:55.792125+00:00"}