{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UXVLTXL6CCLGH5BRBD5OE3H3FN","short_pith_number":"pith:UXVLTXL6","schema_version":"1.0","canonical_sha256":"a5eab9dd7e109663f43108fae26cfb2b7954b8a9f0c13fb82ceb286830761f89","source":{"kind":"arxiv","id":"2301.02903","version":1},"attestation_state":"computed","paper":{"title":"Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Byoungjip Kim, Dasol Hwang, Honglak Lee, Moontae Lee, Sungik Choi","submitted_at":"2023-01-07T17:24:11Z","abstract_excerpt":"Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources. In this paper, we propose a method (BeamCLIP) that can effectively transfer the representations of a large pre-trained multimodal model (CLIP-ViT) into a small target model (e.g., ResNet-18). For unsupervised transfer, we introduce cross-modal similarity matching (CSM) that enables a student model to learn the representations of a teacher model by matching the relative similarity distribution across text prompt embe"},"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":"2301.02903","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-07T17:24:11Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8aade4a04961b043f81714d0cc90e3974dbd28937ff271231fcafa515dfc7ef1","abstract_canon_sha256":"3a4322869bf23d9c81932f94478511c38cc29e44a4d3f2adcbe24614ae499ec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:23.524640Z","signature_b64":"w5zM0eZDUgd0+0qHl5zOuBLnKGLdCUPhnem2s+sLbdcC6GnzRJGBSGmzNzHpEhbX4UnJJfdZVpIls38jHvOzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5eab9dd7e109663f43108fae26cfb2b7954b8a9f0c13fb82ceb286830761f89","last_reissued_at":"2026-07-05T05:31:23.524148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:23.524148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Byoungjip Kim, Dasol Hwang, Honglak Lee, Moontae Lee, Sungik Choi","submitted_at":"2023-01-07T17:24:11Z","abstract_excerpt":"Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources. In this paper, we propose a method (BeamCLIP) that can effectively transfer the representations of a large pre-trained multimodal model (CLIP-ViT) into a small target model (e.g., ResNet-18). For unsupervised transfer, we introduce cross-modal similarity matching (CSM) that enables a student model to learn the representations of a teacher model by matching the relative similarity distribution across text prompt embe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02903","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/2301.02903/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":"2301.02903","created_at":"2026-07-05T05:31:23.524203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02903v1","created_at":"2026-07-05T05:31:23.524203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02903","created_at":"2026-07-05T05:31:23.524203+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXVLTXL6CCLG","created_at":"2026-07-05T05:31:23.524203+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXVLTXL6CCLGH5BR","created_at":"2026-07-05T05:31:23.524203+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXVLTXL6","created_at":"2026-07-05T05:31:23.524203+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/UXVLTXL6CCLGH5BRBD5OE3H3FN","json":"https://pith.science/pith/UXVLTXL6CCLGH5BRBD5OE3H3FN.json","graph_json":"https://pith.science/api/pith-number/UXVLTXL6CCLGH5BRBD5OE3H3FN/graph.json","events_json":"https://pith.science/api/pith-number/UXVLTXL6CCLGH5BRBD5OE3H3FN/events.json","paper":"https://pith.science/paper/UXVLTXL6"},"agent_actions":{"view_html":"https://pith.science/pith/UXVLTXL6CCLGH5BRBD5OE3H3FN","download_json":"https://pith.science/pith/UXVLTXL6CCLGH5BRBD5OE3H3FN.json","view_paper":"https://pith.science/paper/UXVLTXL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02903&json=true","fetch_graph":"https://pith.science/api/pith-number/UXVLTXL6CCLGH5BRBD5OE3H3FN/graph.json","fetch_events":"https://pith.science/api/pith-number/UXVLTXL6CCLGH5BRBD5OE3H3FN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXVLTXL6CCLGH5BRBD5OE3H3FN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXVLTXL6CCLGH5BRBD5OE3H3FN/action/storage_attestation","attest_author":"https://pith.science/pith/UXVLTXL6CCLGH5BRBD5OE3H3FN/action/author_attestation","sign_citation":"https://pith.science/pith/UXVLTXL6CCLGH5BRBD5OE3H3FN/action/citation_signature","submit_replication":"https://pith.science/pith/UXVLTXL6CCLGH5BRBD5OE3H3FN/action/replication_record"}},"created_at":"2026-07-05T05:31:23.524203+00:00","updated_at":"2026-07-05T05:31:23.524203+00:00"}