{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MYB47XHB2K3C4S3HJPHUOD3TNJ","short_pith_number":"pith:MYB47XHB","schema_version":"1.0","canonical_sha256":"6603cfdce1d2b62e4b674bcf470f736a5b589dea6850481938905cd257926db6","source":{"kind":"arxiv","id":"2211.01598","version":1},"attestation_state":"computed","paper":{"title":"Robust Few-shot Learning Without Using any Adversarial Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anirban Chakraborty, Gaurav Kumar Nayak, Inder Khatri, Ruchit Rawal","submitted_at":"2022-11-03T05:58:26Z","abstract_excerpt":"The high cost of acquiring and annotating samples has made the `few-shot' learning problem of prime importance. Existing works mainly focus on improving performance on clean data and overlook robustness concerns on the data perturbed with adversarial noise. Recently, a few efforts have been made to combine the few-shot problem with the robustness objective using sophisticated Meta-Learning techniques. These methods rely on the generation of adversarial samples in every episode of training, which further adds a computational burden. To avoid such time-consuming and complicated procedures, we pr"},"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":"2211.01598","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-03T05:58:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b99387a0b9fc7112126a5acb265a5a8f02e6b0d40f0fcae8d10071be433c8a9d","abstract_canon_sha256":"c0e1540565c0a6c39c6e5f54a99a931778728983a512119031047d3c3d06bbb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:57.814828Z","signature_b64":"TvwpMZr8OYb5nwATPTCQrVDNl9tXlG5u+U3RgT+BXFNASioQW04dBaNWMro/bi0d2iKLO6M9h+auryGyEw6YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6603cfdce1d2b62e4b674bcf470f736a5b589dea6850481938905cd257926db6","last_reissued_at":"2026-07-05T05:12:57.814429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:57.814429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Few-shot Learning Without Using any Adversarial Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anirban Chakraborty, Gaurav Kumar Nayak, Inder Khatri, Ruchit Rawal","submitted_at":"2022-11-03T05:58:26Z","abstract_excerpt":"The high cost of acquiring and annotating samples has made the `few-shot' learning problem of prime importance. Existing works mainly focus on improving performance on clean data and overlook robustness concerns on the data perturbed with adversarial noise. Recently, a few efforts have been made to combine the few-shot problem with the robustness objective using sophisticated Meta-Learning techniques. These methods rely on the generation of adversarial samples in every episode of training, which further adds a computational burden. To avoid such time-consuming and complicated procedures, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01598","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/2211.01598/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":"2211.01598","created_at":"2026-07-05T05:12:57.814498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01598v1","created_at":"2026-07-05T05:12:57.814498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01598","created_at":"2026-07-05T05:12:57.814498+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYB47XHB2K3C","created_at":"2026-07-05T05:12:57.814498+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYB47XHB2K3C4S3H","created_at":"2026-07-05T05:12:57.814498+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYB47XHB","created_at":"2026-07-05T05:12:57.814498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.11220","citing_title":"ANROT-HELANet: Adverserially and Naturally Robust Attention-Based Aggregation Network via The Hellinger Distance for Few-Shot Classification","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYB47XHB2K3C4S3HJPHUOD3TNJ","json":"https://pith.science/pith/MYB47XHB2K3C4S3HJPHUOD3TNJ.json","graph_json":"https://pith.science/api/pith-number/MYB47XHB2K3C4S3HJPHUOD3TNJ/graph.json","events_json":"https://pith.science/api/pith-number/MYB47XHB2K3C4S3HJPHUOD3TNJ/events.json","paper":"https://pith.science/paper/MYB47XHB"},"agent_actions":{"view_html":"https://pith.science/pith/MYB47XHB2K3C4S3HJPHUOD3TNJ","download_json":"https://pith.science/pith/MYB47XHB2K3C4S3HJPHUOD3TNJ.json","view_paper":"https://pith.science/paper/MYB47XHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01598&json=true","fetch_graph":"https://pith.science/api/pith-number/MYB47XHB2K3C4S3HJPHUOD3TNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/MYB47XHB2K3C4S3HJPHUOD3TNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYB47XHB2K3C4S3HJPHUOD3TNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYB47XHB2K3C4S3HJPHUOD3TNJ/action/storage_attestation","attest_author":"https://pith.science/pith/MYB47XHB2K3C4S3HJPHUOD3TNJ/action/author_attestation","sign_citation":"https://pith.science/pith/MYB47XHB2K3C4S3HJPHUOD3TNJ/action/citation_signature","submit_replication":"https://pith.science/pith/MYB47XHB2K3C4S3HJPHUOD3TNJ/action/replication_record"}},"created_at":"2026-07-05T05:12:57.814498+00:00","updated_at":"2026-07-05T05:12:57.814498+00:00"}