{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CBDJ2B2HTMC5XOBZCR5AMYF4AH","short_pith_number":"pith:CBDJ2B2H","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"},"canonical_sha256":"10469d07479b05dbb839147a0660bc01fa5bb47d92e747339625e6ac09484ec7","source":{"kind":"arxiv","id":"2607.22258","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22258","created_at":"2026-07-27T01:20:56Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22258v1","created_at":"2026-07-27T01:20:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22258","created_at":"2026-07-27T01:20:56Z"},{"alias_kind":"pith_short_12","alias_value":"CBDJ2B2HTMC5","created_at":"2026-07-27T01:20:56Z"},{"alias_kind":"pith_short_16","alias_value":"CBDJ2B2HTMC5XOBZ","created_at":"2026-07-27T01:20:56Z"},{"alias_kind":"pith_short_8","alias_value":"CBDJ2B2H","created_at":"2026-07-27T01:20:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CBDJ2B2HTMC5XOBZCR5AMYF4AH","target":"record","payload":{"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"},"canonical_sha256":"10469d07479b05dbb839147a0660bc01fa5bb47d92e747339625e6ac09484ec7","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"},"source_kind":"arxiv","source_id":"2607.22258","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-27T01:20:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ia0+W7dbf6+LT+X+ZRQhQxAmNZAMkoRVal09Bi5PNz2QBSkGDDd++iM8P5nGjbbDnUu1PYAM7ttPCWw0pKqFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:25:41.811820Z"},"content_sha256":"bd59dcd384fe53788feef4f40d8e27a3173d05634549c4540dfcb1bcda829a7b","schema_version":"1.0","event_id":"sha256:bd59dcd384fe53788feef4f40d8e27a3173d05634549c4540dfcb1bcda829a7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CBDJ2B2HTMC5XOBZCR5AMYF4AH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-27T01:20:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VpE8AouKNuAW4JYknZjZVNTsrMuO1Zc2HzJ3pPjlsQOZyyqXone//h5E9cUkEiZYu7IwEHTLYTDvQYaOVMqgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:25:41.812452Z"},"content_sha256":"8cd67b3553e17c323386e87406a841b0adc46ffd6f5351a2e379df4f0d78570a","schema_version":"1.0","event_id":"sha256:8cd67b3553e17c323386e87406a841b0adc46ffd6f5351a2e379df4f0d78570a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/bundle.json","state_url":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T21:25:41Z","links":{"resolver":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH","bundle":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/bundle.json","state":"https://pith.science/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CBDJ2B2HTMC5XOBZCR5AMYF4AH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CBDJ2B2HTMC5XOBZCR5AMYF4AH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bdf7bebec9cd44b4e4e6cea630a28f4ae858da39981ac69cfda544ad1decacaf","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T12:46:03Z","title_canon_sha256":"a342a8a41d2f25707d84260b3552ad8e565faea32ce857f14ef31c3c7ba8e645"},"schema_version":"1.0","source":{"id":"2607.22258","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22258","created_at":"2026-07-27T01:20:56Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22258v1","created_at":"2026-07-27T01:20:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22258","created_at":"2026-07-27T01:20:56Z"},{"alias_kind":"pith_short_12","alias_value":"CBDJ2B2HTMC5","created_at":"2026-07-27T01:20:56Z"},{"alias_kind":"pith_short_16","alias_value":"CBDJ2B2HTMC5XOBZ","created_at":"2026-07-27T01:20:56Z"},{"alias_kind":"pith_short_8","alias_value":"CBDJ2B2H","created_at":"2026-07-27T01:20:56Z"}],"graph_snapshots":[{"event_id":"sha256:8cd67b3553e17c323386e87406a841b0adc46ffd6f5351a2e379df4f0d78570a","target":"graph","created_at":"2026-07-27T01:20:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.22258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Huiyu Zhou, Jianyuan Sun, Nan Xing, Rajeev Raman, Shiqi Su, Xinyu Yang, Yi-Hang Zhu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T12:46:03Z","title":"Class-Balanced Softmax: A Bayes Theory-Based Method for Long-Tailed Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22258","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bd59dcd384fe53788feef4f40d8e27a3173d05634549c4540dfcb1bcda829a7b","target":"record","created_at":"2026-07-27T01:20:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bdf7bebec9cd44b4e4e6cea630a28f4ae858da39981ac69cfda544ad1decacaf","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T12:46:03Z","title_canon_sha256":"a342a8a41d2f25707d84260b3552ad8e565faea32ce857f14ef31c3c7ba8e645"},"schema_version":"1.0","source":{"id":"2607.22258","kind":"arxiv","version":1}},"canonical_sha256":"10469d07479b05dbb839147a0660bc01fa5bb47d92e747339625e6ac09484ec7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10469d07479b05dbb839147a0660bc01fa5bb47d92e747339625e6ac09484ec7","first_computed_at":"2026-07-27T01:20:56.436006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T01:20:56.436006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/l3lUU4IEacRUWADn9oNM8A1U7DQ4jT2r9NpKp8aIoMCAR2t0/W5y6dP0NoiQbzW3I5TluYzZO2ehb8U7ITnDg==","signature_status":"signed_v1","signed_at":"2026-07-27T01:20:56.436879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22258","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd59dcd384fe53788feef4f40d8e27a3173d05634549c4540dfcb1bcda829a7b","sha256:8cd67b3553e17c323386e87406a841b0adc46ffd6f5351a2e379df4f0d78570a"],"state_sha256":"543aa502e9947ded7d195aa9165ca7beedc41346ad3520f833e39cfefabb88a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zv3oz7N2SnK3eoDH1BE8xN0S80er3RqxjOfgYQlOwBSsbsZahA6phq5UObik69UC4WPQacVj+JoDuM3aKCwFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:25:41.818209Z","bundle_sha256":"eab2c5631f9c67a2ab73954904d5b3892ece1828b530880dc4a3a230e0979516"}}