{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NRQK7HAPLJPX7GW7C3LGLPCHFU","short_pith_number":"pith:NRQK7HAP","schema_version":"1.0","canonical_sha256":"6c60af9c0f5a5f7f9adf16d665bc472d2cec12101c15f68364c93a7c318f6667","source":{"kind":"arxiv","id":"1906.08502","version":1},"attestation_state":"computed","paper":{"title":"Efficient data augmentation using graph imputation neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aurelio Uncini, Indro Spinelli, Michele Scarpiniti, Simone Scardapane","submitted_at":"2019-06-20T08:44:03Z","abstract_excerpt":"Recently, data augmentation in the semi-supervised regime, where unlabeled data vastly outnumbers labeled data, has received a considerable attention. In this paper, we describe an efficient technique for this task, exploiting a recent framework we proposed for missing data imputation called graph imputation neural network (GINN). The key idea is to leverage both supervised and unsupervised data to build a graph of similarities between points in the dataset. Then, we augment the dataset by severely damaging a few of the nodes (up to 80\\% of their features), and reconstructing them using a vari"},"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":"1906.08502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-20T08:44:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9846af2a94674432a16f1c980d87b8d959179b03b83b4f794f4cb0e828220d2b","abstract_canon_sha256":"3e9c8cd8e7c0179945b892b42b7661b751804fd9c150307b2777c265980b9f71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:52.308287Z","signature_b64":"+Af4d9d0nXxw+xPSOBA+EAaowxiz0vLrYYNkd2eTdTzJ78Dxsz14HFneE7MS3E/2AOHFq2+kLxIhq1kJHYKWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c60af9c0f5a5f7f9adf16d665bc472d2cec12101c15f68364c93a7c318f6667","last_reissued_at":"2026-05-17T23:42:52.307807Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:52.307807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient data augmentation using graph imputation neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aurelio Uncini, Indro Spinelli, Michele Scarpiniti, Simone Scardapane","submitted_at":"2019-06-20T08:44:03Z","abstract_excerpt":"Recently, data augmentation in the semi-supervised regime, where unlabeled data vastly outnumbers labeled data, has received a considerable attention. In this paper, we describe an efficient technique for this task, exploiting a recent framework we proposed for missing data imputation called graph imputation neural network (GINN). The key idea is to leverage both supervised and unsupervised data to build a graph of similarities between points in the dataset. Then, we augment the dataset by severely damaging a few of the nodes (up to 80\\% of their features), and reconstructing them using a vari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08502","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":""},"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":"1906.08502","created_at":"2026-05-17T23:42:52.307896+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.08502v1","created_at":"2026-05-17T23:42:52.307896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08502","created_at":"2026-05-17T23:42:52.307896+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRQK7HAPLJPX","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRQK7HAPLJPX7GW7","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRQK7HAP","created_at":"2026-05-18T12:33:24.271573+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/NRQK7HAPLJPX7GW7C3LGLPCHFU","json":"https://pith.science/pith/NRQK7HAPLJPX7GW7C3LGLPCHFU.json","graph_json":"https://pith.science/api/pith-number/NRQK7HAPLJPX7GW7C3LGLPCHFU/graph.json","events_json":"https://pith.science/api/pith-number/NRQK7HAPLJPX7GW7C3LGLPCHFU/events.json","paper":"https://pith.science/paper/NRQK7HAP"},"agent_actions":{"view_html":"https://pith.science/pith/NRQK7HAPLJPX7GW7C3LGLPCHFU","download_json":"https://pith.science/pith/NRQK7HAPLJPX7GW7C3LGLPCHFU.json","view_paper":"https://pith.science/paper/NRQK7HAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.08502&json=true","fetch_graph":"https://pith.science/api/pith-number/NRQK7HAPLJPX7GW7C3LGLPCHFU/graph.json","fetch_events":"https://pith.science/api/pith-number/NRQK7HAPLJPX7GW7C3LGLPCHFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRQK7HAPLJPX7GW7C3LGLPCHFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRQK7HAPLJPX7GW7C3LGLPCHFU/action/storage_attestation","attest_author":"https://pith.science/pith/NRQK7HAPLJPX7GW7C3LGLPCHFU/action/author_attestation","sign_citation":"https://pith.science/pith/NRQK7HAPLJPX7GW7C3LGLPCHFU/action/citation_signature","submit_replication":"https://pith.science/pith/NRQK7HAPLJPX7GW7C3LGLPCHFU/action/replication_record"}},"created_at":"2026-05-17T23:42:52.307896+00:00","updated_at":"2026-05-17T23:42:52.307896+00:00"}