{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FJH4LWT5Z2B7LECYCCMDEWGJV3","short_pith_number":"pith:FJH4LWT5","schema_version":"1.0","canonical_sha256":"2a4fc5da7dce83f5905810983258c9aee27500eba3bd2bf9d9cb40352a37074a","source":{"kind":"arxiv","id":"2210.11016","version":1},"attestation_state":"computed","paper":{"title":"Towards Sustainable Self-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ming-Ming Cheng, Pan Zhou, Shanghua Gao, Shuicheng Yan","submitted_at":"2022-10-20T04:49:56Z","abstract_excerpt":"Although increasingly training-expensive, most self-supervised learning (SSL) models have repeatedly been trained from scratch but not fully utilized, since only a few SOTAs are employed for downstream tasks. In this work, we explore a sustainable SSL framework with two major challenges: i) learning a stronger new SSL model based on the existing pretrained SSL model, also called as \"base\" model, in a cost-friendly manner, ii) allowing the training of the new model to be compatible with various base models. We propose a Target-Enhanced Conditional (TEC) scheme which introduces two components to"},"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":"2210.11016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T04:49:56Z","cross_cats_sorted":[],"title_canon_sha256":"0ee25cb6b52f74ad98e19ccd023adb89936881a32dea8f651e7a9253af43b158","abstract_canon_sha256":"a0048635c67ee803f20c54586216397187d2524c9ec57b8316245373e2ebd92e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:43.053159Z","signature_b64":"k6/xoG+Q3Q6Yj9N0YFhn4FGYgP7ks2plRQUa6xqUiu0tfuiwgSev/fyR7pM2WDC3gv+Dp6FUq51jZYdl6gp5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a4fc5da7dce83f5905810983258c9aee27500eba3bd2bf9d9cb40352a37074a","last_reissued_at":"2026-07-05T05:08:43.052774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:43.052774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Sustainable Self-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ming-Ming Cheng, Pan Zhou, Shanghua Gao, Shuicheng Yan","submitted_at":"2022-10-20T04:49:56Z","abstract_excerpt":"Although increasingly training-expensive, most self-supervised learning (SSL) models have repeatedly been trained from scratch but not fully utilized, since only a few SOTAs are employed for downstream tasks. In this work, we explore a sustainable SSL framework with two major challenges: i) learning a stronger new SSL model based on the existing pretrained SSL model, also called as \"base\" model, in a cost-friendly manner, ii) allowing the training of the new model to be compatible with various base models. We propose a Target-Enhanced Conditional (TEC) scheme which introduces two components to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11016","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/2210.11016/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":"2210.11016","created_at":"2026-07-05T05:08:43.052837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11016v1","created_at":"2026-07-05T05:08:43.052837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11016","created_at":"2026-07-05T05:08:43.052837+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJH4LWT5Z2B7","created_at":"2026-07-05T05:08:43.052837+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJH4LWT5Z2B7LECY","created_at":"2026-07-05T05:08:43.052837+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJH4LWT5","created_at":"2026-07-05T05:08:43.052837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22075","citing_title":"Reasoning in machine vision by learning fast and slow thinking","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FJH4LWT5Z2B7LECYCCMDEWGJV3","json":"https://pith.science/pith/FJH4LWT5Z2B7LECYCCMDEWGJV3.json","graph_json":"https://pith.science/api/pith-number/FJH4LWT5Z2B7LECYCCMDEWGJV3/graph.json","events_json":"https://pith.science/api/pith-number/FJH4LWT5Z2B7LECYCCMDEWGJV3/events.json","paper":"https://pith.science/paper/FJH4LWT5"},"agent_actions":{"view_html":"https://pith.science/pith/FJH4LWT5Z2B7LECYCCMDEWGJV3","download_json":"https://pith.science/pith/FJH4LWT5Z2B7LECYCCMDEWGJV3.json","view_paper":"https://pith.science/paper/FJH4LWT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11016&json=true","fetch_graph":"https://pith.science/api/pith-number/FJH4LWT5Z2B7LECYCCMDEWGJV3/graph.json","fetch_events":"https://pith.science/api/pith-number/FJH4LWT5Z2B7LECYCCMDEWGJV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJH4LWT5Z2B7LECYCCMDEWGJV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJH4LWT5Z2B7LECYCCMDEWGJV3/action/storage_attestation","attest_author":"https://pith.science/pith/FJH4LWT5Z2B7LECYCCMDEWGJV3/action/author_attestation","sign_citation":"https://pith.science/pith/FJH4LWT5Z2B7LECYCCMDEWGJV3/action/citation_signature","submit_replication":"https://pith.science/pith/FJH4LWT5Z2B7LECYCCMDEWGJV3/action/replication_record"}},"created_at":"2026-07-05T05:08:43.052837+00:00","updated_at":"2026-07-05T05:08:43.052837+00:00"}