{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BCXZ4XKM5ZDDJGEHHCWMTRSGR7","short_pith_number":"pith:BCXZ4XKM","schema_version":"1.0","canonical_sha256":"08af9e5d4cee4634988738acc9c6468fe7c98103a9670f4b343fa8661207087d","source":{"kind":"arxiv","id":"2010.01809","version":4},"attestation_state":"computed","paper":{"title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Lian, Stella X. Yu, Xudong Wang, Zhongqi Miao, Ziwei Liu","submitted_at":"2020-10-05T06:53:44Z","abstract_excerpt":"Natural data are often long-tail distributed over semantic classes. Existing recognition methods tackle this imbalanced classification by placing more emphasis on the tail data, through class re-balancing/re-weighting or ensembling over different data groups, resulting in increased tail accuracies but reduced head accuracies.\n  We take a dynamic view of the training data and provide a principled model bias and variance analysis as the training data fluctuates: Existing long-tail classifiers invariably increase the model variance and the head-tail model bias gap remains large, due to more and l"},"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":"2010.01809","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-05T06:53:44Z","cross_cats_sorted":[],"title_canon_sha256":"188293f420ac015f213cc6ea47530d514837d7eaa259876e1ff70a273aa3c5ee","abstract_canon_sha256":"370b979e542ed92a320129253e5df9f6516d479e4c1be5fca7746f1b0cc24ea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:00.760052Z","signature_b64":"l3LHH+q+9ZBvmcltcNBVHcPAQ9/fBDqrvtoq3AaISEHLTx4InjbhXiIdxDKCYqlyJzyuvBHLUvIJAQAO9oWUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08af9e5d4cee4634988738acc9c6468fe7c98103a9670f4b343fa8661207087d","last_reissued_at":"2026-07-05T04:19:00.759575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:00.759575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Long Lian, Stella X. Yu, Xudong Wang, Zhongqi Miao, Ziwei Liu","submitted_at":"2020-10-05T06:53:44Z","abstract_excerpt":"Natural data are often long-tail distributed over semantic classes. Existing recognition methods tackle this imbalanced classification by placing more emphasis on the tail data, through class re-balancing/re-weighting or ensembling over different data groups, resulting in increased tail accuracies but reduced head accuracies.\n  We take a dynamic view of the training data and provide a principled model bias and variance analysis as the training data fluctuates: Existing long-tail classifiers invariably increase the model variance and the head-tail model bias gap remains large, due to more and l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01809","kind":"arxiv","version":4},"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/2010.01809/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":"2010.01809","created_at":"2026-07-05T04:19:00.759632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01809v4","created_at":"2026-07-05T04:19:00.759632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01809","created_at":"2026-07-05T04:19:00.759632+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCXZ4XKM5ZDD","created_at":"2026-07-05T04:19:00.759632+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCXZ4XKM5ZDDJGEH","created_at":"2026-07-05T04:19:00.759632+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCXZ4XKM","created_at":"2026-07-05T04:19:00.759632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27696","citing_title":"Class-frequency Guided Noise Schedule for Diffusion Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2406.13187","citing_title":"Decouple then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10047","citing_title":"Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BCXZ4XKM5ZDDJGEHHCWMTRSGR7","json":"https://pith.science/pith/BCXZ4XKM5ZDDJGEHHCWMTRSGR7.json","graph_json":"https://pith.science/api/pith-number/BCXZ4XKM5ZDDJGEHHCWMTRSGR7/graph.json","events_json":"https://pith.science/api/pith-number/BCXZ4XKM5ZDDJGEHHCWMTRSGR7/events.json","paper":"https://pith.science/paper/BCXZ4XKM"},"agent_actions":{"view_html":"https://pith.science/pith/BCXZ4XKM5ZDDJGEHHCWMTRSGR7","download_json":"https://pith.science/pith/BCXZ4XKM5ZDDJGEHHCWMTRSGR7.json","view_paper":"https://pith.science/paper/BCXZ4XKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01809&json=true","fetch_graph":"https://pith.science/api/pith-number/BCXZ4XKM5ZDDJGEHHCWMTRSGR7/graph.json","fetch_events":"https://pith.science/api/pith-number/BCXZ4XKM5ZDDJGEHHCWMTRSGR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCXZ4XKM5ZDDJGEHHCWMTRSGR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCXZ4XKM5ZDDJGEHHCWMTRSGR7/action/storage_attestation","attest_author":"https://pith.science/pith/BCXZ4XKM5ZDDJGEHHCWMTRSGR7/action/author_attestation","sign_citation":"https://pith.science/pith/BCXZ4XKM5ZDDJGEHHCWMTRSGR7/action/citation_signature","submit_replication":"https://pith.science/pith/BCXZ4XKM5ZDDJGEHHCWMTRSGR7/action/replication_record"}},"created_at":"2026-07-05T04:19:00.759632+00:00","updated_at":"2026-07-05T04:19:00.759632+00:00"}