{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OX5VDWYEPADEMWGCP2QIT6PS4E","short_pith_number":"pith:OX5VDWYE","schema_version":"1.0","canonical_sha256":"75fb51db0478064658c27ea089f9f2e1127cb46592ccac5527e3f093684fdf33","source":{"kind":"arxiv","id":"2401.15834","version":1},"attestation_state":"computed","paper":{"title":"Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bastien Pasdeloup, Ian Reid, Jack Valmadre, Jean-Philippe Diguet, Raphael Lafargue, Vincent Gripon, Yassir Bendou","submitted_at":"2024-01-29T01:52:49Z","abstract_excerpt":"When training data is scarce, it is common to make use of a feature extractor that has been pre-trained on a large base dataset, either by fine-tuning its parameters on the ``target'' dataset or by directly adopting its representation as features for a simple classifier. Fine-tuning is ineffective for few-shot learning, since the target dataset contains only a handful of examples. However, directly adopting the features without fine-tuning relies on the base and target distributions being similar enough that these features achieve separability and generalization. This paper investigates whethe"},"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":"2401.15834","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T01:52:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"36a4c1e57c5364402db017594e6a26c312149b34976a2a3eb296ae6ec18d78f1","abstract_canon_sha256":"6631d1417b55ff06635f8607fcdce2242ff0d511f37d314bc0c3c5e251b36919"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:40.236226Z","signature_b64":"/farmP9Xybzip01aUkORGkRUyvClydaunPbWJbY7QB8Imc6pyLk0JlDQt/lU2dK2PsUILy6MxxCbDtf0Gz45Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75fb51db0478064658c27ea089f9f2e1127cb46592ccac5527e3f093684fdf33","last_reissued_at":"2026-07-05T07:38:40.235797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:40.235797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bastien Pasdeloup, Ian Reid, Jack Valmadre, Jean-Philippe Diguet, Raphael Lafargue, Vincent Gripon, Yassir Bendou","submitted_at":"2024-01-29T01:52:49Z","abstract_excerpt":"When training data is scarce, it is common to make use of a feature extractor that has been pre-trained on a large base dataset, either by fine-tuning its parameters on the ``target'' dataset or by directly adopting its representation as features for a simple classifier. Fine-tuning is ineffective for few-shot learning, since the target dataset contains only a handful of examples. However, directly adopting the features without fine-tuning relies on the base and target distributions being similar enough that these features achieve separability and generalization. This paper investigates whethe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15834","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.15834/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":"2401.15834","created_at":"2026-07-05T07:38:40.235866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.15834v1","created_at":"2026-07-05T07:38:40.235866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15834","created_at":"2026-07-05T07:38:40.235866+00:00"},{"alias_kind":"pith_short_12","alias_value":"OX5VDWYEPADE","created_at":"2026-07-05T07:38:40.235866+00:00"},{"alias_kind":"pith_short_16","alias_value":"OX5VDWYEPADEMWGC","created_at":"2026-07-05T07:38:40.235866+00:00"},{"alias_kind":"pith_short_8","alias_value":"OX5VDWYE","created_at":"2026-07-05T07:38:40.235866+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/OX5VDWYEPADEMWGCP2QIT6PS4E","json":"https://pith.science/pith/OX5VDWYEPADEMWGCP2QIT6PS4E.json","graph_json":"https://pith.science/api/pith-number/OX5VDWYEPADEMWGCP2QIT6PS4E/graph.json","events_json":"https://pith.science/api/pith-number/OX5VDWYEPADEMWGCP2QIT6PS4E/events.json","paper":"https://pith.science/paper/OX5VDWYE"},"agent_actions":{"view_html":"https://pith.science/pith/OX5VDWYEPADEMWGCP2QIT6PS4E","download_json":"https://pith.science/pith/OX5VDWYEPADEMWGCP2QIT6PS4E.json","view_paper":"https://pith.science/paper/OX5VDWYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.15834&json=true","fetch_graph":"https://pith.science/api/pith-number/OX5VDWYEPADEMWGCP2QIT6PS4E/graph.json","fetch_events":"https://pith.science/api/pith-number/OX5VDWYEPADEMWGCP2QIT6PS4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OX5VDWYEPADEMWGCP2QIT6PS4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OX5VDWYEPADEMWGCP2QIT6PS4E/action/storage_attestation","attest_author":"https://pith.science/pith/OX5VDWYEPADEMWGCP2QIT6PS4E/action/author_attestation","sign_citation":"https://pith.science/pith/OX5VDWYEPADEMWGCP2QIT6PS4E/action/citation_signature","submit_replication":"https://pith.science/pith/OX5VDWYEPADEMWGCP2QIT6PS4E/action/replication_record"}},"created_at":"2026-07-05T07:38:40.235866+00:00","updated_at":"2026-07-05T07:38:40.235866+00:00"}