{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7PJYONNC5EGSEHDIJ66W6F4JQ7","short_pith_number":"pith:7PJYONNC","schema_version":"1.0","canonical_sha256":"fbd38735a2e90d221c684fbd6f178987f07a4a013559f9d16b081c8ca6f164ff","source":{"kind":"arxiv","id":"2206.15369","version":2},"attestation_state":"computed","paper":{"title":"No Reason for No Supervision: Improved Generalization in Supervised Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Diane Larlus, Karteek Alahari, Mert Bulent Sariyildiz, Yannis Kalantidis","submitted_at":"2022-06-30T15:43:51Z","abstract_excerpt":"We consider the problem of training a deep neural network on a given classification task, e.g., ImageNet-1K (IN1K), so that it excels at both the training task as well as at other (future) transfer tasks. These two seemingly contradictory properties impose a trade-off between improving the model's generalization and maintaining its performance on the original task. Models trained with self-supervised learning tend to generalize better than their supervised counterparts for transfer learning; yet, they still lag behind supervised models on IN1K. In this paper, we propose a supervised learning s"},"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":"2206.15369","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-30T15:43:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"871cc93e5e24d018286b59133e30a294de24ed84e82f9449523c28d9eb30a8cf","abstract_canon_sha256":"47b7ddd1e3e5c4bd8a8be323dcde66529c6df2d2acb5530ed3c94b6104fcbe32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:53.724906Z","signature_b64":"W2m2XBI+St7DDREBkQLQ9xzFCt8MEmWcZ5FGgLNX5a730Xvtabl4D/lWNl9TWA197XRwtvKoJJ4CkvSrRYrVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbd38735a2e90d221c684fbd6f178987f07a4a013559f9d16b081c8ca6f164ff","last_reissued_at":"2026-07-05T05:49:53.724549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:53.724549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No Reason for No Supervision: Improved Generalization in Supervised Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Diane Larlus, Karteek Alahari, Mert Bulent Sariyildiz, Yannis Kalantidis","submitted_at":"2022-06-30T15:43:51Z","abstract_excerpt":"We consider the problem of training a deep neural network on a given classification task, e.g., ImageNet-1K (IN1K), so that it excels at both the training task as well as at other (future) transfer tasks. These two seemingly contradictory properties impose a trade-off between improving the model's generalization and maintaining its performance on the original task. Models trained with self-supervised learning tend to generalize better than their supervised counterparts for transfer learning; yet, they still lag behind supervised models on IN1K. In this paper, we propose a supervised learning s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15369","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.15369/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":"2206.15369","created_at":"2026-07-05T05:49:53.724607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.15369v2","created_at":"2026-07-05T05:49:53.724607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15369","created_at":"2026-07-05T05:49:53.724607+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PJYONNC5EGS","created_at":"2026-07-05T05:49:53.724607+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PJYONNC5EGSEHDI","created_at":"2026-07-05T05:49:53.724607+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PJYONNC","created_at":"2026-07-05T05:49:53.724607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10831","citing_title":"Low-Biased General Annotated Dataset Generation","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PJYONNC5EGSEHDIJ66W6F4JQ7","json":"https://pith.science/pith/7PJYONNC5EGSEHDIJ66W6F4JQ7.json","graph_json":"https://pith.science/api/pith-number/7PJYONNC5EGSEHDIJ66W6F4JQ7/graph.json","events_json":"https://pith.science/api/pith-number/7PJYONNC5EGSEHDIJ66W6F4JQ7/events.json","paper":"https://pith.science/paper/7PJYONNC"},"agent_actions":{"view_html":"https://pith.science/pith/7PJYONNC5EGSEHDIJ66W6F4JQ7","download_json":"https://pith.science/pith/7PJYONNC5EGSEHDIJ66W6F4JQ7.json","view_paper":"https://pith.science/paper/7PJYONNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.15369&json=true","fetch_graph":"https://pith.science/api/pith-number/7PJYONNC5EGSEHDIJ66W6F4JQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/7PJYONNC5EGSEHDIJ66W6F4JQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PJYONNC5EGSEHDIJ66W6F4JQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PJYONNC5EGSEHDIJ66W6F4JQ7/action/storage_attestation","attest_author":"https://pith.science/pith/7PJYONNC5EGSEHDIJ66W6F4JQ7/action/author_attestation","sign_citation":"https://pith.science/pith/7PJYONNC5EGSEHDIJ66W6F4JQ7/action/citation_signature","submit_replication":"https://pith.science/pith/7PJYONNC5EGSEHDIJ66W6F4JQ7/action/replication_record"}},"created_at":"2026-07-05T05:49:53.724607+00:00","updated_at":"2026-07-05T05:49:53.724607+00:00"}