{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XDBY6SF37ECP2Z2YMSOJ2HFPUE","short_pith_number":"pith:XDBY6SF3","schema_version":"1.0","canonical_sha256":"b8c38f48bbf904fd6758649c9d1cafa1130b76b4b644e4b6b9adf3f8cdfe930d","source":{"kind":"arxiv","id":"2403.06726","version":2},"attestation_state":"computed","paper":{"title":"Probabilistic Contrastive Learning for Long-Tailed Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chaoqun Du, Gao Huang, Shiji Song, Yulin Wang","submitted_at":"2024-03-11T13:44:49Z","abstract_excerpt":"Long-tailed distributions frequently emerge in real-world data, where a large number of minority categories contain a limited number of samples. Such imbalance issue considerably impairs the performance of standard supervised learning algorithms, which are mainly designed for balanced training sets. Recent investigations have revealed that supervised contrastive learning exhibits promising potential in alleviating the data imbalance. However, the performance of supervised contrastive learning is plagued by an inherent challenge: it necessitates sufficiently large batches of training data to co"},"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":"2403.06726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T13:44:49Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b50c4ff6d634d1cf221ac022f3e75fbf9f5706ad1bf054721bb22edad80ad845","abstract_canon_sha256":"02c11c6956ee50e2096970e7b0cf1bc72ad8d55a2486ed6544253c0c8064ec72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:04.022721Z","signature_b64":"Q6tw4ppg54ayCOAg2flp3aJC1vY9IiAzGXUhq/9P5GQTNkJXwcFzmtFTrT7eGzQZESnaiRLwIL8WCcGYwEYGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8c38f48bbf904fd6758649c9d1cafa1130b76b4b644e4b6b9adf3f8cdfe930d","last_reissued_at":"2026-07-05T07:56:04.022224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:04.022224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Contrastive Learning for Long-Tailed Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chaoqun Du, Gao Huang, Shiji Song, Yulin Wang","submitted_at":"2024-03-11T13:44:49Z","abstract_excerpt":"Long-tailed distributions frequently emerge in real-world data, where a large number of minority categories contain a limited number of samples. Such imbalance issue considerably impairs the performance of standard supervised learning algorithms, which are mainly designed for balanced training sets. Recent investigations have revealed that supervised contrastive learning exhibits promising potential in alleviating the data imbalance. However, the performance of supervised contrastive learning is plagued by an inherent challenge: it necessitates sufficiently large batches of training data to co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06726","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/2403.06726/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":"2403.06726","created_at":"2026-07-05T07:56:04.022284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06726v2","created_at":"2026-07-05T07:56:04.022284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06726","created_at":"2026-07-05T07:56:04.022284+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDBY6SF37ECP","created_at":"2026-07-05T07:56:04.022284+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDBY6SF37ECP2Z2Y","created_at":"2026-07-05T07:56:04.022284+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDBY6SF3","created_at":"2026-07-05T07:56:04.022284+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/XDBY6SF37ECP2Z2YMSOJ2HFPUE","json":"https://pith.science/pith/XDBY6SF37ECP2Z2YMSOJ2HFPUE.json","graph_json":"https://pith.science/api/pith-number/XDBY6SF37ECP2Z2YMSOJ2HFPUE/graph.json","events_json":"https://pith.science/api/pith-number/XDBY6SF37ECP2Z2YMSOJ2HFPUE/events.json","paper":"https://pith.science/paper/XDBY6SF3"},"agent_actions":{"view_html":"https://pith.science/pith/XDBY6SF37ECP2Z2YMSOJ2HFPUE","download_json":"https://pith.science/pith/XDBY6SF37ECP2Z2YMSOJ2HFPUE.json","view_paper":"https://pith.science/paper/XDBY6SF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06726&json=true","fetch_graph":"https://pith.science/api/pith-number/XDBY6SF37ECP2Z2YMSOJ2HFPUE/graph.json","fetch_events":"https://pith.science/api/pith-number/XDBY6SF37ECP2Z2YMSOJ2HFPUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDBY6SF37ECP2Z2YMSOJ2HFPUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDBY6SF37ECP2Z2YMSOJ2HFPUE/action/storage_attestation","attest_author":"https://pith.science/pith/XDBY6SF37ECP2Z2YMSOJ2HFPUE/action/author_attestation","sign_citation":"https://pith.science/pith/XDBY6SF37ECP2Z2YMSOJ2HFPUE/action/citation_signature","submit_replication":"https://pith.science/pith/XDBY6SF37ECP2Z2YMSOJ2HFPUE/action/replication_record"}},"created_at":"2026-07-05T07:56:04.022284+00:00","updated_at":"2026-07-05T07:56:04.022284+00:00"}