{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WVNHFLA3K3T7MHLGTUGBDAUXY2","short_pith_number":"pith:WVNHFLA3","schema_version":"1.0","canonical_sha256":"b55a72ac1b56e7f61d669d0c118297c6b6804e07f2db715b6d2dc398e33ca8d8","source":{"kind":"arxiv","id":"2408.01031","version":1},"attestation_state":"computed","paper":{"title":"POA: Pre-training Once for Models of All Sizes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo Ye, Huimei He, Jiangwei Lao, Jian Wang, Jingdong Chen, Lei Yu, Lixiang Ru, Ming Yang, Xin Guo, Yingying Zhang","submitted_at":"2024-08-02T06:13:29Z","abstract_excerpt":"Large-scale self-supervised pre-training has paved the way for one foundation model to handle many different vision tasks. Most pre-training methodologies train a single model of a certain size at one time. Nevertheless, various computation or storage constraints in real-world scenarios require substantial efforts to develop a series of models with different sizes to deploy. Thus, in this study, we propose a novel tri-branch self-supervised training framework, termed as POA (Pre-training Once for All), to tackle this aforementioned issue. Our approach introduces an innovative elastic student b"},"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":"2408.01031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-02T06:13:29Z","cross_cats_sorted":[],"title_canon_sha256":"ed4e29143d65e30bf050cac73a17583bb6bec4ea646ce7af10e573b5c337c882","abstract_canon_sha256":"ac8d34fd0df9d91ecdb3e83baff9e7f16af9605428a77ee09aa8e446327ccffb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:26.026582Z","signature_b64":"+8Dw10RBBhVjzLnJDlWnqWJBsMYb943W+ZzbZtRuWMssfQGSyhk5t4CRPw+Dl+eC0kzPjLk2v2xUS50a94TGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b55a72ac1b56e7f61d669d0c118297c6b6804e07f2db715b6d2dc398e33ca8d8","last_reissued_at":"2026-07-05T08:51:26.026164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:26.026164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POA: Pre-training Once for Models of All Sizes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guo Ye, Huimei He, Jiangwei Lao, Jian Wang, Jingdong Chen, Lei Yu, Lixiang Ru, Ming Yang, Xin Guo, Yingying Zhang","submitted_at":"2024-08-02T06:13:29Z","abstract_excerpt":"Large-scale self-supervised pre-training has paved the way for one foundation model to handle many different vision tasks. Most pre-training methodologies train a single model of a certain size at one time. Nevertheless, various computation or storage constraints in real-world scenarios require substantial efforts to develop a series of models with different sizes to deploy. Thus, in this study, we propose a novel tri-branch self-supervised training framework, termed as POA (Pre-training Once for All), to tackle this aforementioned issue. Our approach introduces an innovative elastic student b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01031","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/2408.01031/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":"2408.01031","created_at":"2026-07-05T08:51:26.026220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01031v1","created_at":"2026-07-05T08:51:26.026220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01031","created_at":"2026-07-05T08:51:26.026220+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVNHFLA3K3T7","created_at":"2026-07-05T08:51:26.026220+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVNHFLA3K3T7MHLG","created_at":"2026-07-05T08:51:26.026220+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVNHFLA3","created_at":"2026-07-05T08:51:26.026220+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/WVNHFLA3K3T7MHLGTUGBDAUXY2","json":"https://pith.science/pith/WVNHFLA3K3T7MHLGTUGBDAUXY2.json","graph_json":"https://pith.science/api/pith-number/WVNHFLA3K3T7MHLGTUGBDAUXY2/graph.json","events_json":"https://pith.science/api/pith-number/WVNHFLA3K3T7MHLGTUGBDAUXY2/events.json","paper":"https://pith.science/paper/WVNHFLA3"},"agent_actions":{"view_html":"https://pith.science/pith/WVNHFLA3K3T7MHLGTUGBDAUXY2","download_json":"https://pith.science/pith/WVNHFLA3K3T7MHLGTUGBDAUXY2.json","view_paper":"https://pith.science/paper/WVNHFLA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01031&json=true","fetch_graph":"https://pith.science/api/pith-number/WVNHFLA3K3T7MHLGTUGBDAUXY2/graph.json","fetch_events":"https://pith.science/api/pith-number/WVNHFLA3K3T7MHLGTUGBDAUXY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVNHFLA3K3T7MHLGTUGBDAUXY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVNHFLA3K3T7MHLGTUGBDAUXY2/action/storage_attestation","attest_author":"https://pith.science/pith/WVNHFLA3K3T7MHLGTUGBDAUXY2/action/author_attestation","sign_citation":"https://pith.science/pith/WVNHFLA3K3T7MHLGTUGBDAUXY2/action/citation_signature","submit_replication":"https://pith.science/pith/WVNHFLA3K3T7MHLGTUGBDAUXY2/action/replication_record"}},"created_at":"2026-07-05T08:51:26.026220+00:00","updated_at":"2026-07-05T08:51:26.026220+00:00"}