{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ECYRABQOETJSDERGS6RPBTPU2I","short_pith_number":"pith:ECYRABQO","schema_version":"1.0","canonical_sha256":"20b110060e24d321922697a2f0cdf4d20a6547ab258c9f6beb6cb99be3c6cb63","source":{"kind":"arxiv","id":"2505.24190","version":2},"attestation_state":"computed","paper":{"title":"Provably Improving Generalization of Few-Shot Models with Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bang Tran Khanh, Dung D. Le, Khoat Than, Lan-Cuong Nguyen, Long Tran-Thanh, Quan Nguyen-Tri","submitted_at":"2025-05-30T03:59:45Z","abstract_excerpt":"Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often face performance degradation due to the inherent gap between real and synthetic distributions. To address this limitation, we develop a theoretical framework that quantifies the impact of such distribution discrepancies on supervised learning, specifically in the context of image classification. More importantly, our framework suggests practical ways to genera"},"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":"2505.24190","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T03:59:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8c146ca67912aea477626099ca7ca636cb4d1475cdef9771d3880adbbb6036fa","abstract_canon_sha256":"8d73b2f1b432987fc325c48f8b23dcfb692318aa4e2c707e9c9248433b9e9e0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:51.792703Z","signature_b64":"ahuxYtwknqxHuTEn10BcjPZ/K97AKaHSvFTogN96SWYktOCH+/rWPJNKx+ghw4GXwn3b2YS5mh/jSC2BDK93Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20b110060e24d321922697a2f0cdf4d20a6547ab258c9f6beb6cb99be3c6cb63","last_reissued_at":"2026-07-05T11:26:51.792191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:51.792191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Improving Generalization of Few-Shot Models with Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bang Tran Khanh, Dung D. Le, Khoat Than, Lan-Cuong Nguyen, Long Tran-Thanh, Quan Nguyen-Tri","submitted_at":"2025-05-30T03:59:45Z","abstract_excerpt":"Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often face performance degradation due to the inherent gap between real and synthetic distributions. To address this limitation, we develop a theoretical framework that quantifies the impact of such distribution discrepancies on supervised learning, specifically in the context of image classification. More importantly, our framework suggests practical ways to genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24190","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/2505.24190/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":"2505.24190","created_at":"2026-07-05T11:26:51.792250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24190v2","created_at":"2026-07-05T11:26:51.792250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24190","created_at":"2026-07-05T11:26:51.792250+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECYRABQOETJS","created_at":"2026-07-05T11:26:51.792250+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECYRABQOETJSDERG","created_at":"2026-07-05T11:26:51.792250+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECYRABQO","created_at":"2026-07-05T11:26:51.792250+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/ECYRABQOETJSDERGS6RPBTPU2I","json":"https://pith.science/pith/ECYRABQOETJSDERGS6RPBTPU2I.json","graph_json":"https://pith.science/api/pith-number/ECYRABQOETJSDERGS6RPBTPU2I/graph.json","events_json":"https://pith.science/api/pith-number/ECYRABQOETJSDERGS6RPBTPU2I/events.json","paper":"https://pith.science/paper/ECYRABQO"},"agent_actions":{"view_html":"https://pith.science/pith/ECYRABQOETJSDERGS6RPBTPU2I","download_json":"https://pith.science/pith/ECYRABQOETJSDERGS6RPBTPU2I.json","view_paper":"https://pith.science/paper/ECYRABQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24190&json=true","fetch_graph":"https://pith.science/api/pith-number/ECYRABQOETJSDERGS6RPBTPU2I/graph.json","fetch_events":"https://pith.science/api/pith-number/ECYRABQOETJSDERGS6RPBTPU2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECYRABQOETJSDERGS6RPBTPU2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECYRABQOETJSDERGS6RPBTPU2I/action/storage_attestation","attest_author":"https://pith.science/pith/ECYRABQOETJSDERGS6RPBTPU2I/action/author_attestation","sign_citation":"https://pith.science/pith/ECYRABQOETJSDERGS6RPBTPU2I/action/citation_signature","submit_replication":"https://pith.science/pith/ECYRABQOETJSDERGS6RPBTPU2I/action/replication_record"}},"created_at":"2026-07-05T11:26:51.792250+00:00","updated_at":"2026-07-05T11:26:51.792250+00:00"}