{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CBDJ2B2HTMC5XOBZCR5AMYF4AH","short_pith_number":"pith:CBDJ2B2H","schema_version":"1.0","canonical_sha256":"10469d07479b05dbb839147a0660bc01fa5bb47d92e747339625e6ac09484ec7","source":{"kind":"arxiv","id":"2607.22258","version":1},"attestation_state":"computed","paper":{"title":"Class-Balanced Softmax: A Bayes Theory-Based Method for Long-Tailed Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Huiyu Zhou, Jianyuan Sun, Nan Xing, Rajeev Raman, Shiqi Su, Xinyu Yang, Yi-Hang Zhu","submitted_at":"2026-07-24T12:46:03Z","abstract_excerpt":"Deep learning models using traditional softmax classifiers have achieved remarkable success in various classification tasks. However, their performance degrades significantly on imbalanced datasets. Although Balanced Softmax is widely adopted as a state-of-the-art rebalancing method, it possesses inherent limitations, such as yielding disproportionately lower testing accuracy for tail classes. To mitigate these shortcomings, we propose the Class-Balanced Softmax (CBS). Rooted in a theoretical Bayesian framework and a heuristic power-law assumption, the CBS is a simple logit adjustment that is "},"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":"2607.22258","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T12:46:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a342a8a41d2f25707d84260b3552ad8e565faea32ce857f14ef31c3c7ba8e645","abstract_canon_sha256":"bdf7bebec9cd44b4e4e6cea630a28f4ae858da39981ac69cfda544ad1decacaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:56.436879Z","signature_b64":"/l3lUU4IEacRUWADn9oNM8A1U7DQ4jT2r9NpKp8aIoMCAR2t0/W5y6dP0NoiQbzW3I5TluYzZO2ehb8U7ITnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10469d07479b05dbb839147a0660bc01fa5bb47d92e747339625e6ac09484ec7","last_reissued_at":"2026-07-27T01:20:56.436006Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:56.436006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-Balanced Softmax: A Bayes Theory-Based Method for Long-Tailed Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Huiyu Zhou, Jianyuan Sun, Nan Xing, Rajeev Raman, Shiqi Su, Xinyu Yang, Yi-Hang Zhu","submitted_at":"2026-07-24T12:46:03Z","abstract_excerpt":"Deep learning models using traditional softmax classifiers have achieved remarkable success in various classification tasks. However, their performance degrades significantly on imbalanced datasets. Although Balanced Softmax is widely adopted as a state-of-the-art rebalancing method, it possesses inherent limitations, such as yielding disproportionately lower testing accuracy for tail classes. To mitigate these shortcomings, we propose the Class-Balanced Softmax (CBS). Rooted in a theoretical Bayesian framework and a heuristic power-law assumption, the CBS is a simple logit adjustment that is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22258","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/2607.22258/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":"2607.22258","created_at":"2026-07-27T01:20:56.436468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22258v1","created_at":"2026-07-27T01:20:56.436468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22258","created_at":"2026-07-27T01:20:56.436468+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBDJ2B2HTMC5","created_at":"2026-07-27T01:20:56.436468+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBDJ2B2HTMC5XOBZ","created_at":"2026-07-27T01:20:56.436468+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBDJ2B2H","created_at":"2026-07-27T01:20:56.436468+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/CBDJ2B2HTMC5XOBZCR5AMYF4AH","json":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH.json","graph_json":"https://pith.science/api/pith-number/CBDJ2B2HTMC5XOBZCR5AMYF4AH/graph.json","events_json":"https://pith.science/api/pith-number/CBDJ2B2HTMC5XOBZCR5AMYF4AH/events.json","paper":"https://pith.science/paper/CBDJ2B2H"},"agent_actions":{"view_html":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH","download_json":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH.json","view_paper":"https://pith.science/paper/CBDJ2B2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22258&json=true","fetch_graph":"https://pith.science/api/pith-number/CBDJ2B2HTMC5XOBZCR5AMYF4AH/graph.json","fetch_events":"https://pith.science/api/pith-number/CBDJ2B2HTMC5XOBZCR5AMYF4AH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/action/storage_attestation","attest_author":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/action/author_attestation","sign_citation":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/action/citation_signature","submit_replication":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/action/replication_record"}},"created_at":"2026-07-27T01:20:56.436468+00:00","updated_at":"2026-07-27T01:20:56.436468+00:00"}