{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JTQJ5KFTGG5YQCOGHAXVVREE7V","short_pith_number":"pith:JTQJ5KFT","schema_version":"1.0","canonical_sha256":"4ce09ea8b331bb8809c6382f5ac484fd67ad11b147cc7e98160acde855e018b0","source":{"kind":"arxiv","id":"2111.00899","version":2},"attestation_state":"computed","paper":{"title":"Equivariant Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV","physics.app-ph"],"primary_cat":"cs.CV","authors_text":"Akash Srivastava, Brian Cheung, Charlotte Loh, Li Jing, Marin Solja\\v{c}i\\'c, Pulkit Agrawal, Rumen Dangovski, Seungwook Han","submitted_at":"2021-10-28T17:21:33Z","abstract_excerpt":"In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, the property of invariance is a trivial instance of a broader class called equivariance, which can be intuitively understood as the property that representations transform according to the way the inputs transform. Here, we show that rather than using only invariance, pre-training that encourages non-trivial equivariance to some transformations, while maintaining invariance to ot"},"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":"2111.00899","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-28T17:21:33Z","cross_cats_sorted":["cs.LG","eess.IV","physics.app-ph"],"title_canon_sha256":"c1f2808adc2b412b3169fe940770977d173a5b8929451c40fbbdbac5a3dcf990","abstract_canon_sha256":"4c2fdeb14bc7b86f535f682502033fa03f08d639de384bb4327648cc46a718e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:14.202484Z","signature_b64":"/koI9DbGp4NRCN19aw5LwwTazHEj4UL5PpTmBIZ2OZSOveA83Owxkl/ONIx1wS9stsxM/9X6ll2laeT3Ut36CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ce09ea8b331bb8809c6382f5ac484fd67ad11b147cc7e98160acde855e018b0","last_reissued_at":"2026-07-05T04:05:14.201996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:14.201996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equivariant Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV","physics.app-ph"],"primary_cat":"cs.CV","authors_text":"Akash Srivastava, Brian Cheung, Charlotte Loh, Li Jing, Marin Solja\\v{c}i\\'c, Pulkit Agrawal, Rumen Dangovski, Seungwook Han","submitted_at":"2021-10-28T17:21:33Z","abstract_excerpt":"In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, the property of invariance is a trivial instance of a broader class called equivariance, which can be intuitively understood as the property that representations transform according to the way the inputs transform. Here, we show that rather than using only invariance, pre-training that encourages non-trivial equivariance to some transformations, while maintaining invariance to ot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00899","kind":"arxiv","version":2},"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/2111.00899/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":"2111.00899","created_at":"2026-07-05T04:05:14.202051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00899v2","created_at":"2026-07-05T04:05:14.202051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00899","created_at":"2026-07-05T04:05:14.202051+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTQJ5KFTGG5Y","created_at":"2026-07-05T04:05:14.202051+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTQJ5KFTGG5YQCOG","created_at":"2026-07-05T04:05:14.202051+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTQJ5KFT","created_at":"2026-07-05T04:05:14.202051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00850","citing_title":"Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06395","citing_title":"Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06395","citing_title":"Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTQJ5KFTGG5YQCOGHAXVVREE7V","json":"https://pith.science/pith/JTQJ5KFTGG5YQCOGHAXVVREE7V.json","graph_json":"https://pith.science/api/pith-number/JTQJ5KFTGG5YQCOGHAXVVREE7V/graph.json","events_json":"https://pith.science/api/pith-number/JTQJ5KFTGG5YQCOGHAXVVREE7V/events.json","paper":"https://pith.science/paper/JTQJ5KFT"},"agent_actions":{"view_html":"https://pith.science/pith/JTQJ5KFTGG5YQCOGHAXVVREE7V","download_json":"https://pith.science/pith/JTQJ5KFTGG5YQCOGHAXVVREE7V.json","view_paper":"https://pith.science/paper/JTQJ5KFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00899&json=true","fetch_graph":"https://pith.science/api/pith-number/JTQJ5KFTGG5YQCOGHAXVVREE7V/graph.json","fetch_events":"https://pith.science/api/pith-number/JTQJ5KFTGG5YQCOGHAXVVREE7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTQJ5KFTGG5YQCOGHAXVVREE7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTQJ5KFTGG5YQCOGHAXVVREE7V/action/storage_attestation","attest_author":"https://pith.science/pith/JTQJ5KFTGG5YQCOGHAXVVREE7V/action/author_attestation","sign_citation":"https://pith.science/pith/JTQJ5KFTGG5YQCOGHAXVVREE7V/action/citation_signature","submit_replication":"https://pith.science/pith/JTQJ5KFTGG5YQCOGHAXVVREE7V/action/replication_record"}},"created_at":"2026-07-05T04:05:14.202051+00:00","updated_at":"2026-07-05T04:05:14.202051+00:00"}