{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UXEUYYY3Q5TEIXTKN43PF5FXPO","short_pith_number":"pith:UXEUYYY3","schema_version":"1.0","canonical_sha256":"a5c94c631b8766445e6a6f36f2f4b77ba8d49703807e847c5b2605e65ff3ad81","source":{"kind":"arxiv","id":"2311.03149","version":2},"attestation_state":"computed","paper":{"title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingkun Huang, Gangshan Wu, Limin Wang, Sen Xing, Yu Qiao, Zhiyu Zhao","submitted_at":"2023-11-06T14:44:34Z","abstract_excerpt":"Self-supervised foundation models have shown great potential in computer vision thanks to the pre-training paradigm of masked autoencoding. Scale is a primary factor influencing the performance of these foundation models. However, these large foundation models often result in high computational cost. This paper focuses on pre-training relatively small vision transformer models that could be efficiently adapted to downstream tasks. Specifically, taking inspiration from knowledge distillation in model compression, we propose a new asymmetric masked distillation (AMD) framework for pre-training r"},"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":"2311.03149","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-06T14:44:34Z","cross_cats_sorted":[],"title_canon_sha256":"499b446fe1570a77c79e2c69b4758719360108b1ca82c549e947f3d249aa4aff","abstract_canon_sha256":"e516e36893636928c97eff0d068e10a41451c313a706d8ea7058c0c53d3c51ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:47.554945Z","signature_b64":"8ZDSisqUs1U4yjShZCGdBi1v72VMnO4dZ6RypXkX7Pr/qg/DE6Z3h3a2uDmBHH+dAa/7bXROELHggu6QqZ0/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5c94c631b8766445e6a6f36f2f4b77ba8d49703807e847c5b2605e65ff3ad81","last_reissued_at":"2026-07-05T08:02:47.554493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:47.554493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingkun Huang, Gangshan Wu, Limin Wang, Sen Xing, Yu Qiao, Zhiyu Zhao","submitted_at":"2023-11-06T14:44:34Z","abstract_excerpt":"Self-supervised foundation models have shown great potential in computer vision thanks to the pre-training paradigm of masked autoencoding. Scale is a primary factor influencing the performance of these foundation models. However, these large foundation models often result in high computational cost. This paper focuses on pre-training relatively small vision transformer models that could be efficiently adapted to downstream tasks. Specifically, taking inspiration from knowledge distillation in model compression, we propose a new asymmetric masked distillation (AMD) framework for pre-training r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03149","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/2311.03149/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":"2311.03149","created_at":"2026-07-05T08:02:47.554549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.03149v2","created_at":"2026-07-05T08:02:47.554549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03149","created_at":"2026-07-05T08:02:47.554549+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXEUYYY3Q5TE","created_at":"2026-07-05T08:02:47.554549+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXEUYYY3Q5TEIXTK","created_at":"2026-07-05T08:02:47.554549+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXEUYYY3","created_at":"2026-07-05T08:02:47.554549+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/UXEUYYY3Q5TEIXTKN43PF5FXPO","json":"https://pith.science/pith/UXEUYYY3Q5TEIXTKN43PF5FXPO.json","graph_json":"https://pith.science/api/pith-number/UXEUYYY3Q5TEIXTKN43PF5FXPO/graph.json","events_json":"https://pith.science/api/pith-number/UXEUYYY3Q5TEIXTKN43PF5FXPO/events.json","paper":"https://pith.science/paper/UXEUYYY3"},"agent_actions":{"view_html":"https://pith.science/pith/UXEUYYY3Q5TEIXTKN43PF5FXPO","download_json":"https://pith.science/pith/UXEUYYY3Q5TEIXTKN43PF5FXPO.json","view_paper":"https://pith.science/paper/UXEUYYY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.03149&json=true","fetch_graph":"https://pith.science/api/pith-number/UXEUYYY3Q5TEIXTKN43PF5FXPO/graph.json","fetch_events":"https://pith.science/api/pith-number/UXEUYYY3Q5TEIXTKN43PF5FXPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXEUYYY3Q5TEIXTKN43PF5FXPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXEUYYY3Q5TEIXTKN43PF5FXPO/action/storage_attestation","attest_author":"https://pith.science/pith/UXEUYYY3Q5TEIXTKN43PF5FXPO/action/author_attestation","sign_citation":"https://pith.science/pith/UXEUYYY3Q5TEIXTKN43PF5FXPO/action/citation_signature","submit_replication":"https://pith.science/pith/UXEUYYY3Q5TEIXTKN43PF5FXPO/action/replication_record"}},"created_at":"2026-07-05T08:02:47.554549+00:00","updated_at":"2026-07-05T08:02:47.554549+00:00"}