{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:APUVPSZYNHBQVSQAOFT4X7OJ72","short_pith_number":"pith:APUVPSZY","schema_version":"1.0","canonical_sha256":"03e957cb3869c30aca007167cbfdc9fe80c84db2c377f1f8bbef544b9d696398","source":{"kind":"arxiv","id":"2102.10106","version":3},"attestation_state":"computed","paper":{"title":"Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bernardo Avila-Pires, Chi-Heng Lin, Erik C. Johnson, Eva L. Dyer, Keith B. Hengen, Kiran Bhaskaran-Nair, Lindsey Kitchell, Max Dabagia, Mehdi Azabou, Michal Valko, Mohammad Gheshlaghi Azar, Ran Liu, William Gray-Roncal","submitted_at":"2021-02-19T18:59:59Z","abstract_excerpt":"State-of-the-art methods for self-supervised learning (SSL) build representations by maximizing the similarity between different transformed \"views\" of a sample. Without sufficient diversity in the transformations used to create views, however, it can be difficult to overcome nuisance variables in the data and build rich representations. This motivates the use of the dataset itself to find similar, yet distinct, samples to serve as views for one another. In this paper, we introduce Mine Your Own vieW (MYOW), a new approach for self-supervised learning that looks within the dataset to define di"},"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":"2102.10106","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-19T18:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"2b0235f5792f0d39d15299edee859774c1c7410894b422e6aacbf53afc4bf034","abstract_canon_sha256":"08b16ee51b1dea2f540c2bf00532c5ff58394f0ad2182a069103174941add484"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:56.966278Z","signature_b64":"2Vbvfi2T33pRCOS4W3CueVl5juSRxebOJLCJOL1ALDWwSfBLPgT/f7B1RHilxo7Tjb9oknzY8xXjK0aewwoNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03e957cb3869c30aca007167cbfdc9fe80c84db2c377f1f8bbef544b9d696398","last_reissued_at":"2026-07-05T03:39:56.965829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:56.965829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bernardo Avila-Pires, Chi-Heng Lin, Erik C. Johnson, Eva L. Dyer, Keith B. Hengen, Kiran Bhaskaran-Nair, Lindsey Kitchell, Max Dabagia, Mehdi Azabou, Michal Valko, Mohammad Gheshlaghi Azar, Ran Liu, William Gray-Roncal","submitted_at":"2021-02-19T18:59:59Z","abstract_excerpt":"State-of-the-art methods for self-supervised learning (SSL) build representations by maximizing the similarity between different transformed \"views\" of a sample. Without sufficient diversity in the transformations used to create views, however, it can be difficult to overcome nuisance variables in the data and build rich representations. This motivates the use of the dataset itself to find similar, yet distinct, samples to serve as views for one another. In this paper, we introduce Mine Your Own vieW (MYOW), a new approach for self-supervised learning that looks within the dataset to define di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10106","kind":"arxiv","version":3},"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/2102.10106/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":"2102.10106","created_at":"2026-07-05T03:39:56.965902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.10106v3","created_at":"2026-07-05T03:39:56.965902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10106","created_at":"2026-07-05T03:39:56.965902+00:00"},{"alias_kind":"pith_short_12","alias_value":"APUVPSZYNHBQ","created_at":"2026-07-05T03:39:56.965902+00:00"},{"alias_kind":"pith_short_16","alias_value":"APUVPSZYNHBQVSQA","created_at":"2026-07-05T03:39:56.965902+00:00"},{"alias_kind":"pith_short_8","alias_value":"APUVPSZY","created_at":"2026-07-05T03:39:56.965902+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/APUVPSZYNHBQVSQAOFT4X7OJ72","json":"https://pith.science/pith/APUVPSZYNHBQVSQAOFT4X7OJ72.json","graph_json":"https://pith.science/api/pith-number/APUVPSZYNHBQVSQAOFT4X7OJ72/graph.json","events_json":"https://pith.science/api/pith-number/APUVPSZYNHBQVSQAOFT4X7OJ72/events.json","paper":"https://pith.science/paper/APUVPSZY"},"agent_actions":{"view_html":"https://pith.science/pith/APUVPSZYNHBQVSQAOFT4X7OJ72","download_json":"https://pith.science/pith/APUVPSZYNHBQVSQAOFT4X7OJ72.json","view_paper":"https://pith.science/paper/APUVPSZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.10106&json=true","fetch_graph":"https://pith.science/api/pith-number/APUVPSZYNHBQVSQAOFT4X7OJ72/graph.json","fetch_events":"https://pith.science/api/pith-number/APUVPSZYNHBQVSQAOFT4X7OJ72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APUVPSZYNHBQVSQAOFT4X7OJ72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APUVPSZYNHBQVSQAOFT4X7OJ72/action/storage_attestation","attest_author":"https://pith.science/pith/APUVPSZYNHBQVSQAOFT4X7OJ72/action/author_attestation","sign_citation":"https://pith.science/pith/APUVPSZYNHBQVSQAOFT4X7OJ72/action/citation_signature","submit_replication":"https://pith.science/pith/APUVPSZYNHBQVSQAOFT4X7OJ72/action/replication_record"}},"created_at":"2026-07-05T03:39:56.965902+00:00","updated_at":"2026-07-05T03:39:56.965902+00:00"}