{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:Y7WC326PN5FGUC7VYYQ6G247RB","short_pith_number":"pith:Y7WC326P","schema_version":"1.0","canonical_sha256":"c7ec2debcf6f4a6a0bf5c621e36b9f8849abda8d6b2f46d637aba71d6492bbad","source":{"kind":"arxiv","id":"1703.05175","version":2},"attestation_state":"computed","paper":{"title":"Prototypical Networks for Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jake Snell, Kevin Swersky, Richard S. Zemel","submitted_at":"2017-03-15T14:31:55Z","abstract_excerpt":"We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions "},"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":"1703.05175","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-15T14:31:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8dde77749400066136241c90338377dc2e5bc293414c3190d018bfbcdc516fdd","abstract_canon_sha256":"a9864c6e9f64296c7cbe3ae6e6825075e15bfe8be0902aa035149b33e8ed2688"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:06.951409Z","signature_b64":"/Wc0OSYk53og8l9xKDICOIRf4u0o3ncmw1LRIx9S/SGrNF09dAADlx39NToijJX1fBpEcgI8MyLk9ebYiYbGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7ec2debcf6f4a6a0bf5c621e36b9f8849abda8d6b2f46d637aba71d6492bbad","last_reissued_at":"2026-05-18T00:42:06.950708Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:06.950708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prototypical Networks for Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jake Snell, Kevin Swersky, Richard S. Zemel","submitted_at":"2017-03-15T14:31:55Z","abstract_excerpt":"We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05175","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":""},"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":"1703.05175","created_at":"2026-05-18T00:42:06.950820+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.05175v2","created_at":"2026-05-18T00:42:06.950820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05175","created_at":"2026-05-18T00:42:06.950820+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7WC326PN5FG","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7WC326PN5FGUC7V","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7WC326P","created_at":"2026-05-18T12:31:56.362134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2502.02779","citing_title":"3D Foundation Model for Generalizable Disease Detection in Head Computed Tomography","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16477","citing_title":"Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00779","citing_title":"Using predefined vector systems to speed up neural network multimillion class classification","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2404.08471","citing_title":"Revisiting Feature Prediction for Learning Visual Representations from Video","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7WC326PN5FGUC7VYYQ6G247RB","json":"https://pith.science/pith/Y7WC326PN5FGUC7VYYQ6G247RB.json","graph_json":"https://pith.science/api/pith-number/Y7WC326PN5FGUC7VYYQ6G247RB/graph.json","events_json":"https://pith.science/api/pith-number/Y7WC326PN5FGUC7VYYQ6G247RB/events.json","paper":"https://pith.science/paper/Y7WC326P"},"agent_actions":{"view_html":"https://pith.science/pith/Y7WC326PN5FGUC7VYYQ6G247RB","download_json":"https://pith.science/pith/Y7WC326PN5FGUC7VYYQ6G247RB.json","view_paper":"https://pith.science/paper/Y7WC326P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.05175&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7WC326PN5FGUC7VYYQ6G247RB/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7WC326PN5FGUC7VYYQ6G247RB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7WC326PN5FGUC7VYYQ6G247RB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7WC326PN5FGUC7VYYQ6G247RB/action/storage_attestation","attest_author":"https://pith.science/pith/Y7WC326PN5FGUC7VYYQ6G247RB/action/author_attestation","sign_citation":"https://pith.science/pith/Y7WC326PN5FGUC7VYYQ6G247RB/action/citation_signature","submit_replication":"https://pith.science/pith/Y7WC326PN5FGUC7VYYQ6G247RB/action/replication_record"}},"created_at":"2026-05-18T00:42:06.950820+00:00","updated_at":"2026-05-18T00:42:06.950820+00:00"}