{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L6BRLBOW7YBCD7TJZSNG5JLGEO","short_pith_number":"pith:L6BRLBOW","schema_version":"1.0","canonical_sha256":"5f831585d6fe0221fe69cc9a6ea5662386d31a3a7abb3241c62019dc900057bb","source":{"kind":"arxiv","id":"2408.16266","version":2},"attestation_state":"computed","paper":{"title":"Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Chen, Yanghao Wang","submitted_at":"2024-08-29T05:05:02Z","abstract_excerpt":"Data Augmentation (DA), i.e., synthesizing faithful and diverse samples to expand the original training set, is a prevalent and effective strategy to improve the performance of various data-scarce tasks. With the powerful image generation ability, diffusion-based DA has shown strong performance gains on different image classification benchmarks. In this paper, we analyze today's diffusion-based DA methods, and argue that they cannot take account of both faithfulness and diversity, which are two critical keys for generating high-quality samples and boosting classification performance. To this e"},"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":"2408.16266","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-29T05:05:02Z","cross_cats_sorted":[],"title_canon_sha256":"d7c378dfd6f8e841b2740c81caa6d983c17a8e6aa6d1a56fb224d2ad32f48f54","abstract_canon_sha256":"aa6e9f486b284fbc441cee06b61d3d44e62f254426e9fb2f1b30ae4709da9263"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:28.822782Z","signature_b64":"sECqub+GDGlZ65laHq/+dXxbTnHs+qwaJmA7Vtj4GRtjAUjMJyFPxU0hEyY52wln/bMNKqIr+GuyYzClxT9WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f831585d6fe0221fe69cc9a6ea5662386d31a3a7abb3241c62019dc900057bb","last_reissued_at":"2026-07-05T09:38:28.822298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:28.822298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Chen, Yanghao Wang","submitted_at":"2024-08-29T05:05:02Z","abstract_excerpt":"Data Augmentation (DA), i.e., synthesizing faithful and diverse samples to expand the original training set, is a prevalent and effective strategy to improve the performance of various data-scarce tasks. With the powerful image generation ability, diffusion-based DA has shown strong performance gains on different image classification benchmarks. In this paper, we analyze today's diffusion-based DA methods, and argue that they cannot take account of both faithfulness and diversity, which are two critical keys for generating high-quality samples and boosting classification performance. To this e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16266","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/2408.16266/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":"2408.16266","created_at":"2026-07-05T09:38:28.822377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16266v2","created_at":"2026-07-05T09:38:28.822377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16266","created_at":"2026-07-05T09:38:28.822377+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6BRLBOW7YBC","created_at":"2026-07-05T09:38:28.822377+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6BRLBOW7YBCD7TJ","created_at":"2026-07-05T09:38:28.822377+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6BRLBOW","created_at":"2026-07-05T09:38:28.822377+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/L6BRLBOW7YBCD7TJZSNG5JLGEO","json":"https://pith.science/pith/L6BRLBOW7YBCD7TJZSNG5JLGEO.json","graph_json":"https://pith.science/api/pith-number/L6BRLBOW7YBCD7TJZSNG5JLGEO/graph.json","events_json":"https://pith.science/api/pith-number/L6BRLBOW7YBCD7TJZSNG5JLGEO/events.json","paper":"https://pith.science/paper/L6BRLBOW"},"agent_actions":{"view_html":"https://pith.science/pith/L6BRLBOW7YBCD7TJZSNG5JLGEO","download_json":"https://pith.science/pith/L6BRLBOW7YBCD7TJZSNG5JLGEO.json","view_paper":"https://pith.science/paper/L6BRLBOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16266&json=true","fetch_graph":"https://pith.science/api/pith-number/L6BRLBOW7YBCD7TJZSNG5JLGEO/graph.json","fetch_events":"https://pith.science/api/pith-number/L6BRLBOW7YBCD7TJZSNG5JLGEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6BRLBOW7YBCD7TJZSNG5JLGEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6BRLBOW7YBCD7TJZSNG5JLGEO/action/storage_attestation","attest_author":"https://pith.science/pith/L6BRLBOW7YBCD7TJZSNG5JLGEO/action/author_attestation","sign_citation":"https://pith.science/pith/L6BRLBOW7YBCD7TJZSNG5JLGEO/action/citation_signature","submit_replication":"https://pith.science/pith/L6BRLBOW7YBCD7TJZSNG5JLGEO/action/replication_record"}},"created_at":"2026-07-05T09:38:28.822377+00:00","updated_at":"2026-07-05T09:38:28.822377+00:00"}