{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZXAKDSIK45EMUTE7RUQSD4II6J","short_pith_number":"pith:ZXAKDSIK","schema_version":"1.0","canonical_sha256":"cdc0a1c90ae748ca4c9f8d2121f108f2589f05a3a28bb8b21183a924ce97452f","source":{"kind":"arxiv","id":"2411.10070","version":2},"attestation_state":"computed","paper":{"title":"Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huali Xu, Li Liu, Ming-Ming Cheng, Shuaifeng Zhi, Shuzhou Sun, Tianpeng Liu","submitted_at":"2024-11-15T09:34:07Z","abstract_excerpt":"Existing cross-domain few-shot learning (CDFSL) methods, which develop source-domain training strategies to enhance model transferability, face challenges with large-scale pre-trained models (LMs) due to inaccessible source data and training strategies. Moreover, fine-tuning LMs for CDFSL demands substantial computational resources, limiting practicality. This paper addresses the source-free CDFSL (SF-CDFSL) problem, tackling few-shot learning (FSL) in the target domain using only pre-trained models and a few target samples without source data or strategies. To overcome the challenge of inacce"},"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":"2411.10070","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T09:34:07Z","cross_cats_sorted":[],"title_canon_sha256":"7c92c0416022f42823d368c78493180c94acecb97d05c2f0e14aadcfa0724f84","abstract_canon_sha256":"7f160757e0047e5c00e8dbf635aa916432fb3b687be30e8bb8076d5ea887d534"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:14.393770Z","signature_b64":"EpHewbLqun1JuTy65NwTJDgLrCwtWRW83BBHrfGxfaguSp18I9uqTwOuIRM/52ft50gDH9X7YsWwtLz6yF1NCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdc0a1c90ae748ca4c9f8d2121f108f2589f05a3a28bb8b21183a924ce97452f","last_reissued_at":"2026-07-05T12:11:14.393201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:14.393201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huali Xu, Li Liu, Ming-Ming Cheng, Shuaifeng Zhi, Shuzhou Sun, Tianpeng Liu","submitted_at":"2024-11-15T09:34:07Z","abstract_excerpt":"Existing cross-domain few-shot learning (CDFSL) methods, which develop source-domain training strategies to enhance model transferability, face challenges with large-scale pre-trained models (LMs) due to inaccessible source data and training strategies. Moreover, fine-tuning LMs for CDFSL demands substantial computational resources, limiting practicality. This paper addresses the source-free CDFSL (SF-CDFSL) problem, tackling few-shot learning (FSL) in the target domain using only pre-trained models and a few target samples without source data or strategies. To overcome the challenge of inacce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10070","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/2411.10070/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":"2411.10070","created_at":"2026-07-05T12:11:14.393265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10070v2","created_at":"2026-07-05T12:11:14.393265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10070","created_at":"2026-07-05T12:11:14.393265+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXAKDSIK45EM","created_at":"2026-07-05T12:11:14.393265+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXAKDSIK45EMUTE7","created_at":"2026-07-05T12:11:14.393265+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXAKDSIK","created_at":"2026-07-05T12:11:14.393265+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":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11659","citing_title":"Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXAKDSIK45EMUTE7RUQSD4II6J","json":"https://pith.science/pith/ZXAKDSIK45EMUTE7RUQSD4II6J.json","graph_json":"https://pith.science/api/pith-number/ZXAKDSIK45EMUTE7RUQSD4II6J/graph.json","events_json":"https://pith.science/api/pith-number/ZXAKDSIK45EMUTE7RUQSD4II6J/events.json","paper":"https://pith.science/paper/ZXAKDSIK"},"agent_actions":{"view_html":"https://pith.science/pith/ZXAKDSIK45EMUTE7RUQSD4II6J","download_json":"https://pith.science/pith/ZXAKDSIK45EMUTE7RUQSD4II6J.json","view_paper":"https://pith.science/paper/ZXAKDSIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10070&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXAKDSIK45EMUTE7RUQSD4II6J/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXAKDSIK45EMUTE7RUQSD4II6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXAKDSIK45EMUTE7RUQSD4II6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXAKDSIK45EMUTE7RUQSD4II6J/action/storage_attestation","attest_author":"https://pith.science/pith/ZXAKDSIK45EMUTE7RUQSD4II6J/action/author_attestation","sign_citation":"https://pith.science/pith/ZXAKDSIK45EMUTE7RUQSD4II6J/action/citation_signature","submit_replication":"https://pith.science/pith/ZXAKDSIK45EMUTE7RUQSD4II6J/action/replication_record"}},"created_at":"2026-07-05T12:11:14.393265+00:00","updated_at":"2026-07-05T12:11:14.393265+00:00"}