{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OO236Z6U4DXR6BOBBWR2L6RCTM","short_pith_number":"pith:OO236Z6U","schema_version":"1.0","canonical_sha256":"73b5bf67d4e0ef1f05c10da3a5fa229b14cd295472837fc6466a5198e4870614","source":{"kind":"arxiv","id":"2110.05076","version":5},"attestation_state":"computed","paper":{"title":"A Closer Look at Prototype Classifier for Few-shot Image Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Issei Sato, Mingcheng Hou","submitted_at":"2021-10-11T08:28:43Z","abstract_excerpt":"The prototypical network is a prototype classifier based on meta-learning and is widely used for few-shot learning because it classifies unseen examples by constructing class-specific prototypes without adjusting hyper-parameters during meta-testing. Interestingly, recent research has attracted a lot of attention, showing that training a new linear classifier, which does not use a meta-learning algorithm, performs comparably with the prototypical network. However, the training of a new linear classifier requires the retraining of the classifier every time a new class appears. In this paper, we"},"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":"2110.05076","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-11T08:28:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89f624c35b6d0999a0dd13fe2689ed1a87776d2bcc63250d909a5aeae3f100c3","abstract_canon_sha256":"dc88a0439868227da67caa32ff4916c14b817cf5c320ccbaeb3504fa2f865559"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:43.444071Z","signature_b64":"g2MdP2VWPF/txxER7dGnous/EhDifZbI3m9P6auQ/e1sxSdarr58zmwTHPmbcLsfH223z0xFSZvGw/PGx37gAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73b5bf67d4e0ef1f05c10da3a5fa229b14cd295472837fc6466a5198e4870614","last_reissued_at":"2026-07-05T04:57:43.443647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:43.443647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Closer Look at Prototype Classifier for Few-shot Image Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Issei Sato, Mingcheng Hou","submitted_at":"2021-10-11T08:28:43Z","abstract_excerpt":"The prototypical network is a prototype classifier based on meta-learning and is widely used for few-shot learning because it classifies unseen examples by constructing class-specific prototypes without adjusting hyper-parameters during meta-testing. Interestingly, recent research has attracted a lot of attention, showing that training a new linear classifier, which does not use a meta-learning algorithm, performs comparably with the prototypical network. However, the training of a new linear classifier requires the retraining of the classifier every time a new class appears. In this paper, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05076","kind":"arxiv","version":5},"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/2110.05076/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":"2110.05076","created_at":"2026-07-05T04:57:43.443715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05076v5","created_at":"2026-07-05T04:57:43.443715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05076","created_at":"2026-07-05T04:57:43.443715+00:00"},{"alias_kind":"pith_short_12","alias_value":"OO236Z6U4DXR","created_at":"2026-07-05T04:57:43.443715+00:00"},{"alias_kind":"pith_short_16","alias_value":"OO236Z6U4DXR6BOB","created_at":"2026-07-05T04:57:43.443715+00:00"},{"alias_kind":"pith_short_8","alias_value":"OO236Z6U","created_at":"2026-07-05T04:57:43.443715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10160","citing_title":"Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OO236Z6U4DXR6BOBBWR2L6RCTM","json":"https://pith.science/pith/OO236Z6U4DXR6BOBBWR2L6RCTM.json","graph_json":"https://pith.science/api/pith-number/OO236Z6U4DXR6BOBBWR2L6RCTM/graph.json","events_json":"https://pith.science/api/pith-number/OO236Z6U4DXR6BOBBWR2L6RCTM/events.json","paper":"https://pith.science/paper/OO236Z6U"},"agent_actions":{"view_html":"https://pith.science/pith/OO236Z6U4DXR6BOBBWR2L6RCTM","download_json":"https://pith.science/pith/OO236Z6U4DXR6BOBBWR2L6RCTM.json","view_paper":"https://pith.science/paper/OO236Z6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05076&json=true","fetch_graph":"https://pith.science/api/pith-number/OO236Z6U4DXR6BOBBWR2L6RCTM/graph.json","fetch_events":"https://pith.science/api/pith-number/OO236Z6U4DXR6BOBBWR2L6RCTM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OO236Z6U4DXR6BOBBWR2L6RCTM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OO236Z6U4DXR6BOBBWR2L6RCTM/action/storage_attestation","attest_author":"https://pith.science/pith/OO236Z6U4DXR6BOBBWR2L6RCTM/action/author_attestation","sign_citation":"https://pith.science/pith/OO236Z6U4DXR6BOBBWR2L6RCTM/action/citation_signature","submit_replication":"https://pith.science/pith/OO236Z6U4DXR6BOBBWR2L6RCTM/action/replication_record"}},"created_at":"2026-07-05T04:57:43.443715+00:00","updated_at":"2026-07-05T04:57:43.443715+00:00"}