{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DT5AEHTLI2YWIANZJ5HG2ADWHP","short_pith_number":"pith:DT5AEHTL","schema_version":"1.0","canonical_sha256":"1cfa021e6b46b16401b94f4e6d00763be4591d90200da57652fc82577a5c9947","source":{"kind":"arxiv","id":"2109.09883","version":1},"attestation_state":"computed","paper":{"title":"On the Importance of Distractors for Few-Shot Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jos\\'eM.F. Moura, Rajshekhar Das, Yu-Xiong Wang","submitted_at":"2021-09-20T23:35:56Z","abstract_excerpt":"Few-shot classification aims at classifying categories of a novel task by learning from just a few (typically, 1 to 5) labelled examples. An effective approach to few-shot classification involves a prior model trained on a large-sample base domain, which is then finetuned over the novel few-shot task to yield generalizable representations. However, task-specific finetuning is prone to overfitting due to the lack of enough training examples. To alleviate this issue, we propose a new finetuning approach based on contrastive learning that reuses unlabelled examples from the base domain in the for"},"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":"2109.09883","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-20T23:35:56Z","cross_cats_sorted":[],"title_canon_sha256":"013d32414ccaf882b7fb4b0b56d736b14e20f5d0c543b1357d06db8cc3294719","abstract_canon_sha256":"1c5c56662de892746a1cb8b69ea118e7f228e0fd8aea6c7d4faba529f46174bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:55.496674Z","signature_b64":"7R4aXTPoo0f+DxZxWFNgq763si4JXS6sosXB7QVpEnW0NnkeFWWXcrWV9vY+klVG9+wdK6pISHVpOAu6bXnsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cfa021e6b46b16401b94f4e6d00763be4591d90200da57652fc82577a5c9947","last_reissued_at":"2026-07-05T03:15:55.496202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:55.496202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Importance of Distractors for Few-Shot Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jos\\'eM.F. Moura, Rajshekhar Das, Yu-Xiong Wang","submitted_at":"2021-09-20T23:35:56Z","abstract_excerpt":"Few-shot classification aims at classifying categories of a novel task by learning from just a few (typically, 1 to 5) labelled examples. An effective approach to few-shot classification involves a prior model trained on a large-sample base domain, which is then finetuned over the novel few-shot task to yield generalizable representations. However, task-specific finetuning is prone to overfitting due to the lack of enough training examples. To alleviate this issue, we propose a new finetuning approach based on contrastive learning that reuses unlabelled examples from the base domain in the for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09883","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/2109.09883/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":"2109.09883","created_at":"2026-07-05T03:15:55.496257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09883v1","created_at":"2026-07-05T03:15:55.496257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09883","created_at":"2026-07-05T03:15:55.496257+00:00"},{"alias_kind":"pith_short_12","alias_value":"DT5AEHTLI2YW","created_at":"2026-07-05T03:15:55.496257+00:00"},{"alias_kind":"pith_short_16","alias_value":"DT5AEHTLI2YWIANZ","created_at":"2026-07-05T03:15:55.496257+00:00"},{"alias_kind":"pith_short_8","alias_value":"DT5AEHTL","created_at":"2026-07-05T03:15:55.496257+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/DT5AEHTLI2YWIANZJ5HG2ADWHP","json":"https://pith.science/pith/DT5AEHTLI2YWIANZJ5HG2ADWHP.json","graph_json":"https://pith.science/api/pith-number/DT5AEHTLI2YWIANZJ5HG2ADWHP/graph.json","events_json":"https://pith.science/api/pith-number/DT5AEHTLI2YWIANZJ5HG2ADWHP/events.json","paper":"https://pith.science/paper/DT5AEHTL"},"agent_actions":{"view_html":"https://pith.science/pith/DT5AEHTLI2YWIANZJ5HG2ADWHP","download_json":"https://pith.science/pith/DT5AEHTLI2YWIANZJ5HG2ADWHP.json","view_paper":"https://pith.science/paper/DT5AEHTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09883&json=true","fetch_graph":"https://pith.science/api/pith-number/DT5AEHTLI2YWIANZJ5HG2ADWHP/graph.json","fetch_events":"https://pith.science/api/pith-number/DT5AEHTLI2YWIANZJ5HG2ADWHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DT5AEHTLI2YWIANZJ5HG2ADWHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DT5AEHTLI2YWIANZJ5HG2ADWHP/action/storage_attestation","attest_author":"https://pith.science/pith/DT5AEHTLI2YWIANZJ5HG2ADWHP/action/author_attestation","sign_citation":"https://pith.science/pith/DT5AEHTLI2YWIANZJ5HG2ADWHP/action/citation_signature","submit_replication":"https://pith.science/pith/DT5AEHTLI2YWIANZJ5HG2ADWHP/action/replication_record"}},"created_at":"2026-07-05T03:15:55.496257+00:00","updated_at":"2026-07-05T03:15:55.496257+00:00"}