{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QPGVASOJAYTIHOSJL5YVCRJRVR","short_pith_number":"pith:QPGVASOJ","schema_version":"1.0","canonical_sha256":"83cd5049c9062683ba495f71514531ac5d5c3a55de54586286086acf4dfb6ba6","source":{"kind":"arxiv","id":"2010.08887","version":2},"attestation_state":"computed","paper":{"title":"i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chun-Liang Li, Honglak Lee, Jinwoo Shin, Kibok Lee, Kihyuk Sohn, Yian Zhu","submitted_at":"2020-10-17T23:32:26Z","abstract_excerpt":"Contrastive representation learning has shown to be effective to learn representations from unlabeled data. However, much progress has been made in vision domains relying on data augmentations carefully designed using domain knowledge. In this work, we propose i-Mix, a simple yet effective domain-agnostic regularization strategy for improving contrastive representation learning. We cast contrastive learning as training a non-parametric classifier by assigning a unique virtual class to each data in a batch. Then, data instances are mixed in both the input and virtual label spaces, providing mor"},"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":"2010.08887","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-17T23:32:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"692a9052b7f5404fe2ef663b777221ab9401f23053405444a29698589aae330c","abstract_canon_sha256":"0d17c6da85e2a7de334492d622a7cf8f0f22b92f9d6a666ae2cf191dbe6000d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:11.511511Z","signature_b64":"Vub49UJtQUJMxOPbuOWKNigfahIv7LTbUHVzzblaXXO+yXG8x7ig9tOEzUX5e2p/A2zg6Oy/vqOmxDO1Y4G1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83cd5049c9062683ba495f71514531ac5d5c3a55de54586286086acf4dfb6ba6","last_reissued_at":"2026-07-05T02:24:11.511025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:11.511025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chun-Liang Li, Honglak Lee, Jinwoo Shin, Kibok Lee, Kihyuk Sohn, Yian Zhu","submitted_at":"2020-10-17T23:32:26Z","abstract_excerpt":"Contrastive representation learning has shown to be effective to learn representations from unlabeled data. However, much progress has been made in vision domains relying on data augmentations carefully designed using domain knowledge. In this work, we propose i-Mix, a simple yet effective domain-agnostic regularization strategy for improving contrastive representation learning. We cast contrastive learning as training a non-parametric classifier by assigning a unique virtual class to each data in a batch. Then, data instances are mixed in both the input and virtual label spaces, providing mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08887","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/2010.08887/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":"2010.08887","created_at":"2026-07-05T02:24:11.511084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08887v2","created_at":"2026-07-05T02:24:11.511084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08887","created_at":"2026-07-05T02:24:11.511084+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPGVASOJAYTI","created_at":"2026-07-05T02:24:11.511084+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPGVASOJAYTIHOSJ","created_at":"2026-07-05T02:24:11.511084+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPGVASOJ","created_at":"2026-07-05T02:24:11.511084+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13607","citing_title":"PreMixer: MLP-Based Pre-training Enhanced MLP-Mixers for Large-scale Traffic Forecasting","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QPGVASOJAYTIHOSJL5YVCRJRVR","json":"https://pith.science/pith/QPGVASOJAYTIHOSJL5YVCRJRVR.json","graph_json":"https://pith.science/api/pith-number/QPGVASOJAYTIHOSJL5YVCRJRVR/graph.json","events_json":"https://pith.science/api/pith-number/QPGVASOJAYTIHOSJL5YVCRJRVR/events.json","paper":"https://pith.science/paper/QPGVASOJ"},"agent_actions":{"view_html":"https://pith.science/pith/QPGVASOJAYTIHOSJL5YVCRJRVR","download_json":"https://pith.science/pith/QPGVASOJAYTIHOSJL5YVCRJRVR.json","view_paper":"https://pith.science/paper/QPGVASOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08887&json=true","fetch_graph":"https://pith.science/api/pith-number/QPGVASOJAYTIHOSJL5YVCRJRVR/graph.json","fetch_events":"https://pith.science/api/pith-number/QPGVASOJAYTIHOSJL5YVCRJRVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPGVASOJAYTIHOSJL5YVCRJRVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPGVASOJAYTIHOSJL5YVCRJRVR/action/storage_attestation","attest_author":"https://pith.science/pith/QPGVASOJAYTIHOSJL5YVCRJRVR/action/author_attestation","sign_citation":"https://pith.science/pith/QPGVASOJAYTIHOSJL5YVCRJRVR/action/citation_signature","submit_replication":"https://pith.science/pith/QPGVASOJAYTIHOSJL5YVCRJRVR/action/replication_record"}},"created_at":"2026-07-05T02:24:11.511084+00:00","updated_at":"2026-07-05T02:24:11.511084+00:00"}