{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DUQMOAQAIW7L7NQZPDYYIUY24T","short_pith_number":"pith:DUQMOAQA","schema_version":"1.0","canonical_sha256":"1d20c7020045bebfb61978f184531ae4c782e88077cde2812ef8bea8f227911f","source":{"kind":"arxiv","id":"1708.02735","version":1},"attestation_state":"computed","paper":{"title":"Gaussian Prototypical Networks for Few-Shot Learning on Omniglot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Stanislav Fort","submitted_at":"2017-08-09T06:53:31Z","abstract_excerpt":"We propose a novel architecture for $k$-shot classification on the Omniglot dataset. Building on prototypical networks, we extend their architecture to what we call Gaussian prototypical networks. Prototypical networks learn a map between images and embedding vectors, and use their clustering for classification. In our model, a part of the encoder output is interpreted as a confidence region estimate about the embedding point, and expressed as a Gaussian covariance matrix. Our network then constructs a direction and class dependent distance metric on the embedding space, using uncertainties of"},"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":"1708.02735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-09T06:53:31Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"cbefceaa6943610bd2cc0036798d1da5842d6d811b45be48fbb657fe3fd0d60b","abstract_canon_sha256":"da32c7146261bbdb7e08aea6f8f62d5423bbf571595ce2125c05e7062064b99b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:19.740980Z","signature_b64":"4QELNc+NQMe8pfAN13YicAMskUy++0IC2LjO4lKLAO05hmBl3LEOxbzRlm0axRm1QIJ0ULm/8YvfF4njxlidCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d20c7020045bebfb61978f184531ae4c782e88077cde2812ef8bea8f227911f","last_reissued_at":"2026-05-18T00:38:19.740349Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:19.740349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Prototypical Networks for Few-Shot Learning on Omniglot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Stanislav Fort","submitted_at":"2017-08-09T06:53:31Z","abstract_excerpt":"We propose a novel architecture for $k$-shot classification on the Omniglot dataset. Building on prototypical networks, we extend their architecture to what we call Gaussian prototypical networks. Prototypical networks learn a map between images and embedding vectors, and use their clustering for classification. In our model, a part of the encoder output is interpreted as a confidence region estimate about the embedding point, and expressed as a Gaussian covariance matrix. Our network then constructs a direction and class dependent distance metric on the embedding space, using uncertainties of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02735","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":"1708.02735","created_at":"2026-05-18T00:38:19.740442+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.02735v1","created_at":"2026-05-18T00:38:19.740442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02735","created_at":"2026-05-18T00:38:19.740442+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUQMOAQAIW7L","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUQMOAQAIW7L7NQZ","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUQMOAQA","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.18326","citing_title":"Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ABHFA-Net","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUQMOAQAIW7L7NQZPDYYIUY24T","json":"https://pith.science/pith/DUQMOAQAIW7L7NQZPDYYIUY24T.json","graph_json":"https://pith.science/api/pith-number/DUQMOAQAIW7L7NQZPDYYIUY24T/graph.json","events_json":"https://pith.science/api/pith-number/DUQMOAQAIW7L7NQZPDYYIUY24T/events.json","paper":"https://pith.science/paper/DUQMOAQA"},"agent_actions":{"view_html":"https://pith.science/pith/DUQMOAQAIW7L7NQZPDYYIUY24T","download_json":"https://pith.science/pith/DUQMOAQAIW7L7NQZPDYYIUY24T.json","view_paper":"https://pith.science/paper/DUQMOAQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.02735&json=true","fetch_graph":"https://pith.science/api/pith-number/DUQMOAQAIW7L7NQZPDYYIUY24T/graph.json","fetch_events":"https://pith.science/api/pith-number/DUQMOAQAIW7L7NQZPDYYIUY24T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUQMOAQAIW7L7NQZPDYYIUY24T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUQMOAQAIW7L7NQZPDYYIUY24T/action/storage_attestation","attest_author":"https://pith.science/pith/DUQMOAQAIW7L7NQZPDYYIUY24T/action/author_attestation","sign_citation":"https://pith.science/pith/DUQMOAQAIW7L7NQZPDYYIUY24T/action/citation_signature","submit_replication":"https://pith.science/pith/DUQMOAQAIW7L7NQZPDYYIUY24T/action/replication_record"}},"created_at":"2026-05-18T00:38:19.740442+00:00","updated_at":"2026-05-18T00:38:19.740442+00:00"}