{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LNOGOYSPNVGTXCWHGTB5WUMF45","short_pith_number":"pith:LNOGOYSP","schema_version":"1.0","canonical_sha256":"5b5c67624f6d4d3b8ac734c3db5185e76a48d844fa2660d7b86486f652809dca","source":{"kind":"arxiv","id":"2112.04367","version":1},"attestation_state":"computed","paper":{"title":"On visual self-supervision and its effect on model robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Diane Oyen, Garrett Kenyon, Michal Kucer","submitted_at":"2021-12-08T16:22:02Z","abstract_excerpt":"Recent self-supervision methods have found success in learning feature representations that could rival ones from full supervision, and have been shown to be beneficial to the model in several ways: for example improving models robustness and out-of-distribution detection. In our paper, we conduct an empirical study to understand more precisely in what way can self-supervised learning - as a pre-training technique or part of adversarial training - affects model robustness to $l_2$ and $l_{\\infty}$ adversarial perturbations and natural image corruptions. Self-supervision can indeed improve mode"},"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":"2112.04367","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T16:22:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"584d01353239d346845325aaee5188745dafb51387c53542ac4e50e60b2c876f","abstract_canon_sha256":"314867df26326a2432d52fb699cf90227073dc2de6ff45ce623881e749206367"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:08.922415Z","signature_b64":"KTNgP2OoJ6rZBQP/d5f/CMrxQtzoBFV5njpCtyI+pQIHWvC4/UBX1zBQ2/8Ph7FP8QmTYQQO1yRJ2Z5JaKMUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b5c67624f6d4d3b8ac734c3db5185e76a48d844fa2660d7b86486f652809dca","last_reissued_at":"2026-07-05T03:39:08.921941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:08.921941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On visual self-supervision and its effect on model robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Diane Oyen, Garrett Kenyon, Michal Kucer","submitted_at":"2021-12-08T16:22:02Z","abstract_excerpt":"Recent self-supervision methods have found success in learning feature representations that could rival ones from full supervision, and have been shown to be beneficial to the model in several ways: for example improving models robustness and out-of-distribution detection. In our paper, we conduct an empirical study to understand more precisely in what way can self-supervised learning - as a pre-training technique or part of adversarial training - affects model robustness to $l_2$ and $l_{\\infty}$ adversarial perturbations and natural image corruptions. Self-supervision can indeed improve mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04367","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/2112.04367/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":"2112.04367","created_at":"2026-07-05T03:39:08.922005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.04367v1","created_at":"2026-07-05T03:39:08.922005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04367","created_at":"2026-07-05T03:39:08.922005+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNOGOYSPNVGT","created_at":"2026-07-05T03:39:08.922005+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNOGOYSPNVGTXCWH","created_at":"2026-07-05T03:39:08.922005+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNOGOYSP","created_at":"2026-07-05T03:39:08.922005+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/LNOGOYSPNVGTXCWHGTB5WUMF45","json":"https://pith.science/pith/LNOGOYSPNVGTXCWHGTB5WUMF45.json","graph_json":"https://pith.science/api/pith-number/LNOGOYSPNVGTXCWHGTB5WUMF45/graph.json","events_json":"https://pith.science/api/pith-number/LNOGOYSPNVGTXCWHGTB5WUMF45/events.json","paper":"https://pith.science/paper/LNOGOYSP"},"agent_actions":{"view_html":"https://pith.science/pith/LNOGOYSPNVGTXCWHGTB5WUMF45","download_json":"https://pith.science/pith/LNOGOYSPNVGTXCWHGTB5WUMF45.json","view_paper":"https://pith.science/paper/LNOGOYSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.04367&json=true","fetch_graph":"https://pith.science/api/pith-number/LNOGOYSPNVGTXCWHGTB5WUMF45/graph.json","fetch_events":"https://pith.science/api/pith-number/LNOGOYSPNVGTXCWHGTB5WUMF45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNOGOYSPNVGTXCWHGTB5WUMF45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNOGOYSPNVGTXCWHGTB5WUMF45/action/storage_attestation","attest_author":"https://pith.science/pith/LNOGOYSPNVGTXCWHGTB5WUMF45/action/author_attestation","sign_citation":"https://pith.science/pith/LNOGOYSPNVGTXCWHGTB5WUMF45/action/citation_signature","submit_replication":"https://pith.science/pith/LNOGOYSPNVGTXCWHGTB5WUMF45/action/replication_record"}},"created_at":"2026-07-05T03:39:08.922005+00:00","updated_at":"2026-07-05T03:39:08.922005+00:00"}