{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WJSPGNRGRG2XJ3FDP653JYTP4F","short_pith_number":"pith:WJSPGNRG","canonical_record":{"source":{"id":"1810.11730","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-27T23:09:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f48defcbf95bd5d5f7dab3cacd287e9005cb836d581a83cd575717063472758d","abstract_canon_sha256":"9a6c21adce0a726871bf94e09ca056069bc9a30200475580e53a7ffa27fe3b85"},"schema_version":"1.0"},"canonical_sha256":"b264f3362689b574eca37fbbb4e26fe170050eb6ecd0fd3a1c2f76d76fddf8b8","source":{"kind":"arxiv","id":"1810.11730","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11730","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11730v3","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11730","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"WJSPGNRGRG2X","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WJSPGNRGRG2XJ3FD","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WJSPGNRG","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WJSPGNRGRG2XJ3FDP653JYTP4F","target":"record","payload":{"canonical_record":{"source":{"id":"1810.11730","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-27T23:09:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f48defcbf95bd5d5f7dab3cacd287e9005cb836d581a83cd575717063472758d","abstract_canon_sha256":"9a6c21adce0a726871bf94e09ca056069bc9a30200475580e53a7ffa27fe3b85"},"schema_version":"1.0"},"canonical_sha256":"b264f3362689b574eca37fbbb4e26fe170050eb6ecd0fd3a1c2f76d76fddf8b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:22.733864Z","signature_b64":"9d0JhSsA/dH8uha1TPjt/An+LBtRzR3F4KwVHFVISP5fCzHQ0ihk2s+f5uG607DTowvchsWHUt7JWZUwnz9RDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b264f3362689b574eca37fbbb4e26fe170050eb6ecd0fd3a1c2f76d76fddf8b8","last_reissued_at":"2026-05-17T23:58:22.733118Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:22.733118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.11730","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zs8OStyUf/AKYlZzPnDKWbloMwh0slaGGfIMgaM/gmDso9RCsJp49PEYo4+yNC+zsb2zsigU1lXWLcLfnFQ/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:55:06.503835Z"},"content_sha256":"c89d375c8a535c8683527cb1f5471fe79e177a5fe06da036ff1fb46b26ac0297","schema_version":"1.0","event_id":"sha256:c89d375c8a535c8683527cb1f5471fe79e177a5fe06da036ff1fb46b26ac0297"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WJSPGNRGRG2XJ3FDP653JYTP4F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alireza Zareian, Hang Gao, Hanwang Zhang, Shih-Fu Chang, Zheng Shou","submitted_at":"2018-10-27T23:09:10Z","abstract_excerpt":"Deep neural networks suffer from over-fitting and catastrophic forgetting when trained with small data. One natural remedy for this problem is data augmentation, which has been recently shown to be effective. However, previous works either assume that intra-class variances can always be generalized to new classes, or employ naive generation methods to hallucinate finite examples without modeling their latent distributions. In this work, we propose Covariance-Preserving Adversarial Augmentation Networks to overcome existing limits of low-shot learning. Specifically, a novel Generative Adversari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11730","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:58:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"12TthL0Xrp1s7VAhaav/wwM8Z/DOx4NChHFqcPsEZArcTLVZmlYJjB7a6GadckrMZVFWNYEARY13O9w73g9DCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T01:55:06.504423Z"},"content_sha256":"a4c7142fa47495a9a17caeff1d22fd999ad4ef8410167ef48b453b495ac68d2b","schema_version":"1.0","event_id":"sha256:a4c7142fa47495a9a17caeff1d22fd999ad4ef8410167ef48b453b495ac68d2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WJSPGNRGRG2XJ3FDP653JYTP4F/bundle.json","state_url":"https://pith.science/pith/WJSPGNRGRG2XJ3FDP653JYTP4F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WJSPGNRGRG2XJ3FDP653JYTP4F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T01:55:06Z","links":{"resolver":"https://pith.science/pith/WJSPGNRGRG2XJ3FDP653JYTP4F","bundle":"https://pith.science/pith/WJSPGNRGRG2XJ3FDP653JYTP4F/bundle.json","state":"https://pith.science/pith/WJSPGNRGRG2XJ3FDP653JYTP4F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WJSPGNRGRG2XJ3FDP653JYTP4F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WJSPGNRGRG2XJ3FDP653JYTP4F","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9a6c21adce0a726871bf94e09ca056069bc9a30200475580e53a7ffa27fe3b85","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-27T23:09:10Z","title_canon_sha256":"f48defcbf95bd5d5f7dab3cacd287e9005cb836d581a83cd575717063472758d"},"schema_version":"1.0","source":{"id":"1810.11730","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11730","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11730v3","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11730","created_at":"2026-05-17T23:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"WJSPGNRGRG2X","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WJSPGNRGRG2XJ3FD","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WJSPGNRG","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:a4c7142fa47495a9a17caeff1d22fd999ad4ef8410167ef48b453b495ac68d2b","target":"graph","created_at":"2026-05-17T23:58:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Deep neural networks suffer from over-fitting and catastrophic forgetting when trained with small data. One natural remedy for this problem is data augmentation, which has been recently shown to be effective. However, previous works either assume that intra-class variances can always be generalized to new classes, or employ naive generation methods to hallucinate finite examples without modeling their latent distributions. In this work, we propose Covariance-Preserving Adversarial Augmentation Networks to overcome existing limits of low-shot learning. Specifically, a novel Generative Adversari","authors_text":"Alireza Zareian, Hang Gao, Hanwang Zhang, Shih-Fu Chang, Zheng Shou","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-27T23:09:10Z","title":"Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11730","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c89d375c8a535c8683527cb1f5471fe79e177a5fe06da036ff1fb46b26ac0297","target":"record","created_at":"2026-05-17T23:58:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9a6c21adce0a726871bf94e09ca056069bc9a30200475580e53a7ffa27fe3b85","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-27T23:09:10Z","title_canon_sha256":"f48defcbf95bd5d5f7dab3cacd287e9005cb836d581a83cd575717063472758d"},"schema_version":"1.0","source":{"id":"1810.11730","kind":"arxiv","version":3}},"canonical_sha256":"b264f3362689b574eca37fbbb4e26fe170050eb6ecd0fd3a1c2f76d76fddf8b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b264f3362689b574eca37fbbb4e26fe170050eb6ecd0fd3a1c2f76d76fddf8b8","first_computed_at":"2026-05-17T23:58:22.733118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:22.733118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9d0JhSsA/dH8uha1TPjt/An+LBtRzR3F4KwVHFVISP5fCzHQ0ihk2s+f5uG607DTowvchsWHUt7JWZUwnz9RDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:22.733864Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.11730","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c89d375c8a535c8683527cb1f5471fe79e177a5fe06da036ff1fb46b26ac0297","sha256:a4c7142fa47495a9a17caeff1d22fd999ad4ef8410167ef48b453b495ac68d2b"],"state_sha256":"6a52de1735668517ce8c86d535a7066eab95ca0c0d76c301bfa827abec7dadd9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qlumLONJRXsAmjRG65L0xghA01Gt1KL1uDSuMa/02Qu29I06uJ4dQzVqjOyrkQLp40wK1HkMOzHWcZg9HsxAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T01:55:06.507253Z","bundle_sha256":"b25a769a216cea6dee7d1ae5341c4d8ca461113044af636324588450f4254796"}}