{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QL7EDQE2J45MK2CDUIXBYIFD34","short_pith_number":"pith:QL7EDQE2","schema_version":"1.0","canonical_sha256":"82fe41c09a4f3ac56843a22e1c20a3df3c4acda625b69539ab6b03d581f0e2c0","source":{"kind":"arxiv","id":"2209.15525","version":3},"attestation_state":"computed","paper":{"title":"Slimmable Networks for Contrastive Self-supervised Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Linchao Zhu, Shuai Zhao, Xiaohan Wang, Yi Yang","submitted_at":"2022-09-30T15:15:05Z","abstract_excerpt":"Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. Mainstream solutions to this problem rely mainly on knowledge distillation, which involves a two-stage procedure: first training a large teacher model and then distilling it to improve the generalization ability of smaller ones. In this work, we introduce another one-stage solution to obtain pre-trained small models without the need for extra teachers, namely, slimmable networks for contrastive self-supervised learning (SlimCLR). A slimmable network consists of a full network and "},"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":"2209.15525","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T15:15:05Z","cross_cats_sorted":[],"title_canon_sha256":"26f8eab5a8d501c5b433e9c4c07d3eacbe53212b7550644e36b0b442a92961fd","abstract_canon_sha256":"2882d3ab20d26aa24acfe740a8c468c68f588b7724d05800ab82ab0f103fb3c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:23.030303Z","signature_b64":"vkFfwN3KrhbPZB9UNuRjiF341K5GxUh+h5S5qK09/VX9/Hmcx77gL8rlxpLnC38jgf+bi9F+FwxmPLZdTZxuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82fe41c09a4f3ac56843a22e1c20a3df3c4acda625b69539ab6b03d581f0e2c0","last_reissued_at":"2026-07-05T08:49:23.029843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:23.029843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Slimmable Networks for Contrastive Self-supervised Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Linchao Zhu, Shuai Zhao, Xiaohan Wang, Yi Yang","submitted_at":"2022-09-30T15:15:05Z","abstract_excerpt":"Self-supervised learning makes significant progress in pre-training large models, but struggles with small models. Mainstream solutions to this problem rely mainly on knowledge distillation, which involves a two-stage procedure: first training a large teacher model and then distilling it to improve the generalization ability of smaller ones. In this work, we introduce another one-stage solution to obtain pre-trained small models without the need for extra teachers, namely, slimmable networks for contrastive self-supervised learning (SlimCLR). A slimmable network consists of a full network and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15525","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/2209.15525/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":"2209.15525","created_at":"2026-07-05T08:49:23.029912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.15525v3","created_at":"2026-07-05T08:49:23.029912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15525","created_at":"2026-07-05T08:49:23.029912+00:00"},{"alias_kind":"pith_short_12","alias_value":"QL7EDQE2J45M","created_at":"2026-07-05T08:49:23.029912+00:00"},{"alias_kind":"pith_short_16","alias_value":"QL7EDQE2J45MK2CD","created_at":"2026-07-05T08:49:23.029912+00:00"},{"alias_kind":"pith_short_8","alias_value":"QL7EDQE2","created_at":"2026-07-05T08:49:23.029912+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/QL7EDQE2J45MK2CDUIXBYIFD34","json":"https://pith.science/pith/QL7EDQE2J45MK2CDUIXBYIFD34.json","graph_json":"https://pith.science/api/pith-number/QL7EDQE2J45MK2CDUIXBYIFD34/graph.json","events_json":"https://pith.science/api/pith-number/QL7EDQE2J45MK2CDUIXBYIFD34/events.json","paper":"https://pith.science/paper/QL7EDQE2"},"agent_actions":{"view_html":"https://pith.science/pith/QL7EDQE2J45MK2CDUIXBYIFD34","download_json":"https://pith.science/pith/QL7EDQE2J45MK2CDUIXBYIFD34.json","view_paper":"https://pith.science/paper/QL7EDQE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.15525&json=true","fetch_graph":"https://pith.science/api/pith-number/QL7EDQE2J45MK2CDUIXBYIFD34/graph.json","fetch_events":"https://pith.science/api/pith-number/QL7EDQE2J45MK2CDUIXBYIFD34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QL7EDQE2J45MK2CDUIXBYIFD34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QL7EDQE2J45MK2CDUIXBYIFD34/action/storage_attestation","attest_author":"https://pith.science/pith/QL7EDQE2J45MK2CDUIXBYIFD34/action/author_attestation","sign_citation":"https://pith.science/pith/QL7EDQE2J45MK2CDUIXBYIFD34/action/citation_signature","submit_replication":"https://pith.science/pith/QL7EDQE2J45MK2CDUIXBYIFD34/action/replication_record"}},"created_at":"2026-07-05T08:49:23.029912+00:00","updated_at":"2026-07-05T08:49:23.029912+00:00"}