{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7SJ2VG7J5NLOOKVZUGYTS354RD","short_pith_number":"pith:7SJ2VG7J","schema_version":"1.0","canonical_sha256":"fc93aa9be9eb56e72ab9a1b1396fbc88d7cf040f78afe6bd89b14bb1a78a292c","source":{"kind":"arxiv","id":"2111.02679","version":1},"attestation_state":"computed","paper":{"title":"MixSiam: A Mixture-based Approach to Self-supervised Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, Tianhao Zhao, Xiaoyang Guo, Yutian Lin","submitted_at":"2021-11-04T08:12:47Z","abstract_excerpt":"Recently contrastive learning has shown significant progress in learning visual representations from unlabeled data. The core idea is training the backbone to be invariant to different augmentations of an instance. While most methods only maximize the feature similarity between two augmented data, we further generate more challenging training samples and force the model to keep predicting discriminative representation on these hard samples. In this paper, we propose MixSiam, a mixture-based approach upon the traditional siamese network. On the one hand, we input two augmented images of an inst"},"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":"2111.02679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-04T08:12:47Z","cross_cats_sorted":[],"title_canon_sha256":"78f313c2f35eaddeff58799f75baaa2a436b0f77d60557222535ce6fa4b69186","abstract_canon_sha256":"afeb3d98b7ce24e03bb0ffaa4fd69ecb4febf3a88b96b2cedaf8718cfcbf4153"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:07.304245Z","signature_b64":"qgd6+7unau44G5mxFWWhik4bGEUbvK+MS3jqr7nT6Fb7SYsk8YeHujwPsrd8ht9n1mLvyVY+gpHboi8hd5izCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc93aa9be9eb56e72ab9a1b1396fbc88d7cf040f78afe6bd89b14bb1a78a292c","last_reissued_at":"2026-07-05T03:29:07.303693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:07.303693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixSiam: A Mixture-based Approach to Self-supervised Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Du, Tianhao Zhao, Xiaoyang Guo, Yutian Lin","submitted_at":"2021-11-04T08:12:47Z","abstract_excerpt":"Recently contrastive learning has shown significant progress in learning visual representations from unlabeled data. The core idea is training the backbone to be invariant to different augmentations of an instance. While most methods only maximize the feature similarity between two augmented data, we further generate more challenging training samples and force the model to keep predicting discriminative representation on these hard samples. In this paper, we propose MixSiam, a mixture-based approach upon the traditional siamese network. On the one hand, we input two augmented images of an inst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.02679","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/2111.02679/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":"2111.02679","created_at":"2026-07-05T03:29:07.303755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.02679v1","created_at":"2026-07-05T03:29:07.303755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.02679","created_at":"2026-07-05T03:29:07.303755+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SJ2VG7J5NLO","created_at":"2026-07-05T03:29:07.303755+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SJ2VG7J5NLOOKVZ","created_at":"2026-07-05T03:29:07.303755+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SJ2VG7J","created_at":"2026-07-05T03:29:07.303755+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/7SJ2VG7J5NLOOKVZUGYTS354RD","json":"https://pith.science/pith/7SJ2VG7J5NLOOKVZUGYTS354RD.json","graph_json":"https://pith.science/api/pith-number/7SJ2VG7J5NLOOKVZUGYTS354RD/graph.json","events_json":"https://pith.science/api/pith-number/7SJ2VG7J5NLOOKVZUGYTS354RD/events.json","paper":"https://pith.science/paper/7SJ2VG7J"},"agent_actions":{"view_html":"https://pith.science/pith/7SJ2VG7J5NLOOKVZUGYTS354RD","download_json":"https://pith.science/pith/7SJ2VG7J5NLOOKVZUGYTS354RD.json","view_paper":"https://pith.science/paper/7SJ2VG7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.02679&json=true","fetch_graph":"https://pith.science/api/pith-number/7SJ2VG7J5NLOOKVZUGYTS354RD/graph.json","fetch_events":"https://pith.science/api/pith-number/7SJ2VG7J5NLOOKVZUGYTS354RD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SJ2VG7J5NLOOKVZUGYTS354RD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SJ2VG7J5NLOOKVZUGYTS354RD/action/storage_attestation","attest_author":"https://pith.science/pith/7SJ2VG7J5NLOOKVZUGYTS354RD/action/author_attestation","sign_citation":"https://pith.science/pith/7SJ2VG7J5NLOOKVZUGYTS354RD/action/citation_signature","submit_replication":"https://pith.science/pith/7SJ2VG7J5NLOOKVZUGYTS354RD/action/replication_record"}},"created_at":"2026-07-05T03:29:07.303755+00:00","updated_at":"2026-07-05T03:29:07.303755+00:00"}