{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q7SSYDTSZNW5IU63QAZ3WSDTS7","short_pith_number":"pith:Q7SSYDTS","schema_version":"1.0","canonical_sha256":"87e52c0e72cb6dd453db8033bb487397e67d8263bbc617aef5fbb9d5dcdeaf4c","source":{"kind":"arxiv","id":"2412.19101","version":1},"attestation_state":"computed","paper":{"title":"Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ran Ma, Ruixuan Li, Yixiong Zou, Yuhua Li","submitted_at":"2024-12-26T07:43:01Z","abstract_excerpt":"Cross-Domain Few-Shot Learning (CDFSL) requires the model to transfer knowledge from the data-abundant source domain to data-scarce target domains for fast adaptation, where the large domain gap makes CDFSL a challenging problem. Masked Autoencoder (MAE) excels in effectively using unlabeled data and learning image's global structures, enhancing model generalization and robustness. However, in the CDFSL task with significant domain shifts, we find MAE even shows lower performance than the baseline supervised models. In this paper, we first delve into this phenomenon for an interpretation. We f"},"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":"2412.19101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T07:43:01Z","cross_cats_sorted":[],"title_canon_sha256":"42eb9443b174e3b58150ab1ac20d6d8a3eba8c2d492d338bae43480297a7a4d7","abstract_canon_sha256":"a98a2fbe07b192bafe8732d6924e7a1d5e52829f6a0a0958b066645aefe6b120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:16.152813Z","signature_b64":"ZiZEgVx/6OdtJCfWpj8XRWLSQ/no8LrtmdHl3mN3+aVWHMceAs6iLv/JFETWTJtjbcHVGm8vKoi8KivRkA0OCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87e52c0e72cb6dd453db8033bb487397e67d8263bbc617aef5fbb9d5dcdeaf4c","last_reissued_at":"2026-07-05T09:54:16.152376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:16.152376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reconstruction Target Matters in Masked Image Modeling for Cross-Domain Few-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ran Ma, Ruixuan Li, Yixiong Zou, Yuhua Li","submitted_at":"2024-12-26T07:43:01Z","abstract_excerpt":"Cross-Domain Few-Shot Learning (CDFSL) requires the model to transfer knowledge from the data-abundant source domain to data-scarce target domains for fast adaptation, where the large domain gap makes CDFSL a challenging problem. Masked Autoencoder (MAE) excels in effectively using unlabeled data and learning image's global structures, enhancing model generalization and robustness. However, in the CDFSL task with significant domain shifts, we find MAE even shows lower performance than the baseline supervised models. In this paper, we first delve into this phenomenon for an interpretation. We f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19101","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/2412.19101/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":"2412.19101","created_at":"2026-07-05T09:54:16.152435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19101v1","created_at":"2026-07-05T09:54:16.152435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19101","created_at":"2026-07-05T09:54:16.152435+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7SSYDTSZNW5","created_at":"2026-07-05T09:54:16.152435+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7SSYDTSZNW5IU63","created_at":"2026-07-05T09:54:16.152435+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7SSYDTS","created_at":"2026-07-05T09:54:16.152435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25799","citing_title":"Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29776","citing_title":"Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7SSYDTSZNW5IU63QAZ3WSDTS7","json":"https://pith.science/pith/Q7SSYDTSZNW5IU63QAZ3WSDTS7.json","graph_json":"https://pith.science/api/pith-number/Q7SSYDTSZNW5IU63QAZ3WSDTS7/graph.json","events_json":"https://pith.science/api/pith-number/Q7SSYDTSZNW5IU63QAZ3WSDTS7/events.json","paper":"https://pith.science/paper/Q7SSYDTS"},"agent_actions":{"view_html":"https://pith.science/pith/Q7SSYDTSZNW5IU63QAZ3WSDTS7","download_json":"https://pith.science/pith/Q7SSYDTSZNW5IU63QAZ3WSDTS7.json","view_paper":"https://pith.science/paper/Q7SSYDTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19101&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7SSYDTSZNW5IU63QAZ3WSDTS7/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7SSYDTSZNW5IU63QAZ3WSDTS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7SSYDTSZNW5IU63QAZ3WSDTS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7SSYDTSZNW5IU63QAZ3WSDTS7/action/storage_attestation","attest_author":"https://pith.science/pith/Q7SSYDTSZNW5IU63QAZ3WSDTS7/action/author_attestation","sign_citation":"https://pith.science/pith/Q7SSYDTSZNW5IU63QAZ3WSDTS7/action/citation_signature","submit_replication":"https://pith.science/pith/Q7SSYDTSZNW5IU63QAZ3WSDTS7/action/replication_record"}},"created_at":"2026-07-05T09:54:16.152435+00:00","updated_at":"2026-07-05T09:54:16.152435+00:00"}