{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4M5U2NTBL56XHVHOORRJQNCHNH","short_pith_number":"pith:4M5U2NTB","schema_version":"1.0","canonical_sha256":"e33b4d36615f7d73d4ee746298344769d2331c78453ffbe04e5a59ec53bb1d19","source":{"kind":"arxiv","id":"2310.15105","version":4},"attestation_state":"computed","paper":{"title":"FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bochao Zou, Huimin Ma, Huishuai Zhang, Kun Song, Weiran Huang","submitted_at":"2023-10-23T17:12:01Z","abstract_excerpt":"Due to the limited availability of data, existing few-shot learning methods trained from scratch fail to achieve satisfactory performance. In contrast, large-scale pre-trained models such as CLIP demonstrate remarkable few-shot and zero-shot capabilities. To enhance the performance of pre-trained models for downstream tasks, fine-tuning the model on downstream data is frequently necessary. However, fine-tuning the pre-trained model leads to a decrease in its generalizability in the presence of distribution shift, while the limited number of samples in few-shot learning makes the model highly s"},"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":"2310.15105","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T17:12:01Z","cross_cats_sorted":[],"title_canon_sha256":"fb979d4ce619a46201f7c2fee21429bb819ca56cf3bbdc1595285bac66b980df","abstract_canon_sha256":"8cd986fdd6c5f1ff2015aebe1e26a80d7f7d433fee599348a9f91da87cc39bbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:45.321731Z","signature_b64":"PpWaNynn75v7iK+zij06xqPglqizbC2V/z22h3dEe/CsojDxlMRcgo1dyyKon1UrxWx/NrW2+BLGI2C6hUz6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e33b4d36615f7d73d4ee746298344769d2331c78453ffbe04e5a59ec53bb1d19","last_reissued_at":"2026-07-05T07:13:45.321219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:45.321219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bochao Zou, Huimin Ma, Huishuai Zhang, Kun Song, Weiran Huang","submitted_at":"2023-10-23T17:12:01Z","abstract_excerpt":"Due to the limited availability of data, existing few-shot learning methods trained from scratch fail to achieve satisfactory performance. In contrast, large-scale pre-trained models such as CLIP demonstrate remarkable few-shot and zero-shot capabilities. To enhance the performance of pre-trained models for downstream tasks, fine-tuning the model on downstream data is frequently necessary. However, fine-tuning the pre-trained model leads to a decrease in its generalizability in the presence of distribution shift, while the limited number of samples in few-shot learning makes the model highly s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15105","kind":"arxiv","version":4},"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/2310.15105/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":"2310.15105","created_at":"2026-07-05T07:13:45.321269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15105v4","created_at":"2026-07-05T07:13:45.321269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15105","created_at":"2026-07-05T07:13:45.321269+00:00"},{"alias_kind":"pith_short_12","alias_value":"4M5U2NTBL56X","created_at":"2026-07-05T07:13:45.321269+00:00"},{"alias_kind":"pith_short_16","alias_value":"4M5U2NTBL56XHVHO","created_at":"2026-07-05T07:13:45.321269+00:00"},{"alias_kind":"pith_short_8","alias_value":"4M5U2NTB","created_at":"2026-07-05T07:13:45.321269+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/4M5U2NTBL56XHVHOORRJQNCHNH","json":"https://pith.science/pith/4M5U2NTBL56XHVHOORRJQNCHNH.json","graph_json":"https://pith.science/api/pith-number/4M5U2NTBL56XHVHOORRJQNCHNH/graph.json","events_json":"https://pith.science/api/pith-number/4M5U2NTBL56XHVHOORRJQNCHNH/events.json","paper":"https://pith.science/paper/4M5U2NTB"},"agent_actions":{"view_html":"https://pith.science/pith/4M5U2NTBL56XHVHOORRJQNCHNH","download_json":"https://pith.science/pith/4M5U2NTBL56XHVHOORRJQNCHNH.json","view_paper":"https://pith.science/paper/4M5U2NTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15105&json=true","fetch_graph":"https://pith.science/api/pith-number/4M5U2NTBL56XHVHOORRJQNCHNH/graph.json","fetch_events":"https://pith.science/api/pith-number/4M5U2NTBL56XHVHOORRJQNCHNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4M5U2NTBL56XHVHOORRJQNCHNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4M5U2NTBL56XHVHOORRJQNCHNH/action/storage_attestation","attest_author":"https://pith.science/pith/4M5U2NTBL56XHVHOORRJQNCHNH/action/author_attestation","sign_citation":"https://pith.science/pith/4M5U2NTBL56XHVHOORRJQNCHNH/action/citation_signature","submit_replication":"https://pith.science/pith/4M5U2NTBL56XHVHOORRJQNCHNH/action/replication_record"}},"created_at":"2026-07-05T07:13:45.321269+00:00","updated_at":"2026-07-05T07:13:45.321269+00:00"}