{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XNDFE3GSYS6HESJYIX5XPJKLPH","short_pith_number":"pith:XNDFE3GS","schema_version":"1.0","canonical_sha256":"bb46526cd2c4bc72493845fb77a54b79f33e0e421314355e2279f3dc2a8da8a0","source":{"kind":"arxiv","id":"2310.10090","version":1},"attestation_state":"computed","paper":{"title":"Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fang Liu, Licheng Jiao, Lingling Li, Shuyuan Yang, Xu Liu, Yanbiao Ma","submitted_at":"2023-10-16T05:50:34Z","abstract_excerpt":"In scenarios with long-tailed distributions, the model's ability to identify tail classes is limited due to the under-representation of tail samples. Class rebalancing, information augmentation, and other techniques have been proposed to facilitate models to learn the potential distribution of tail classes. The disadvantage is that these methods generally pursue models with balanced class accuracy on the data manifold, while ignoring the ability of the model to resist interference. By constructing noisy data manifold, we found that the robustness of models trained on unbalanced data has a long"},"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":"2310.10090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T05:50:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84bd1caab51d1a6d9645b093d12d3bbce4822f80164da632e501bc762e4fc273","abstract_canon_sha256":"50b112f9926e73296d5c04549740708f383bf567a03cadace35efdaa3827dc90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:15.143621Z","signature_b64":"J99w17L3+NWmBmOMNwxRTdgvQXKQ0pYzZLdMJUEh8jf6jX7qoBrsCS7lMkcFvGy/QKYXqpY2wM/9xruu06wRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb46526cd2c4bc72493845fb77a54b79f33e0e421314355e2279f3dc2a8da8a0","last_reissued_at":"2026-07-05T07:01:15.143169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:15.143169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fang Liu, Licheng Jiao, Lingling Li, Shuyuan Yang, Xu Liu, Yanbiao Ma","submitted_at":"2023-10-16T05:50:34Z","abstract_excerpt":"In scenarios with long-tailed distributions, the model's ability to identify tail classes is limited due to the under-representation of tail samples. Class rebalancing, information augmentation, and other techniques have been proposed to facilitate models to learn the potential distribution of tail classes. The disadvantage is that these methods generally pursue models with balanced class accuracy on the data manifold, while ignoring the ability of the model to resist interference. By constructing noisy data manifold, we found that the robustness of models trained on unbalanced data has a long"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10090","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/2310.10090/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":"2310.10090","created_at":"2026-07-05T07:01:15.143225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10090v1","created_at":"2026-07-05T07:01:15.143225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10090","created_at":"2026-07-05T07:01:15.143225+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNDFE3GSYS6H","created_at":"2026-07-05T07:01:15.143225+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNDFE3GSYS6HESJY","created_at":"2026-07-05T07:01:15.143225+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNDFE3GS","created_at":"2026-07-05T07:01:15.143225+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/XNDFE3GSYS6HESJYIX5XPJKLPH","json":"https://pith.science/pith/XNDFE3GSYS6HESJYIX5XPJKLPH.json","graph_json":"https://pith.science/api/pith-number/XNDFE3GSYS6HESJYIX5XPJKLPH/graph.json","events_json":"https://pith.science/api/pith-number/XNDFE3GSYS6HESJYIX5XPJKLPH/events.json","paper":"https://pith.science/paper/XNDFE3GS"},"agent_actions":{"view_html":"https://pith.science/pith/XNDFE3GSYS6HESJYIX5XPJKLPH","download_json":"https://pith.science/pith/XNDFE3GSYS6HESJYIX5XPJKLPH.json","view_paper":"https://pith.science/paper/XNDFE3GS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10090&json=true","fetch_graph":"https://pith.science/api/pith-number/XNDFE3GSYS6HESJYIX5XPJKLPH/graph.json","fetch_events":"https://pith.science/api/pith-number/XNDFE3GSYS6HESJYIX5XPJKLPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNDFE3GSYS6HESJYIX5XPJKLPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNDFE3GSYS6HESJYIX5XPJKLPH/action/storage_attestation","attest_author":"https://pith.science/pith/XNDFE3GSYS6HESJYIX5XPJKLPH/action/author_attestation","sign_citation":"https://pith.science/pith/XNDFE3GSYS6HESJYIX5XPJKLPH/action/citation_signature","submit_replication":"https://pith.science/pith/XNDFE3GSYS6HESJYIX5XPJKLPH/action/replication_record"}},"created_at":"2026-07-05T07:01:15.143225+00:00","updated_at":"2026-07-05T07:01:15.143225+00:00"}