{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZQVRXBMCYDODLWS6SA4KHQY24Q","short_pith_number":"pith:ZQVRXBMC","canonical_record":{"source":{"id":"2509.05307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-22T23:11:43Z","cross_cats_sorted":[],"title_canon_sha256":"04c422e7c5e48cdd80abe13fb6ef022a02bf3cb64a31e9b107bcb0350ccb81f1","abstract_canon_sha256":"d7bdafb81f22a1a0700f05c57604936edae07b52df3129c72dc8301524b2245a"},"schema_version":"1.0"},"canonical_sha256":"cc2b1b8582c0dc35da5e9038a3c31ae434c9d6c45b92346135c549ffabf91fdd","source":{"kind":"arxiv","id":"2509.05307","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05307","created_at":"2026-07-05T12:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05307v1","created_at":"2026-07-05T12:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05307","created_at":"2026-07-05T12:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZQVRXBMCYDOD","created_at":"2026-07-05T12:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZQVRXBMCYDODLWS6","created_at":"2026-07-05T12:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZQVRXBMC","created_at":"2026-07-05T12:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZQVRXBMCYDODLWS6SA4KHQY24Q","target":"record","payload":{"canonical_record":{"source":{"id":"2509.05307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-22T23:11:43Z","cross_cats_sorted":[],"title_canon_sha256":"04c422e7c5e48cdd80abe13fb6ef022a02bf3cb64a31e9b107bcb0350ccb81f1","abstract_canon_sha256":"d7bdafb81f22a1a0700f05c57604936edae07b52df3129c72dc8301524b2245a"},"schema_version":"1.0"},"canonical_sha256":"cc2b1b8582c0dc35da5e9038a3c31ae434c9d6c45b92346135c549ffabf91fdd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:44.695575Z","signature_b64":"SEbiboDzC4IphgEXclIZYP/4giIZHg85OV4DdAIX9hkZsAqTglY8AlrOjqgWPchvlNnKprgkH/A/EzNh7MaMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc2b1b8582c0dc35da5e9038a3c31ae434c9d6c45b92346135c549ffabf91fdd","last_reissued_at":"2026-07-05T12:05:44.695064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:44.695064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.05307","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":"2026-07-05T12:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A8DdXDL7NjkXYCFkaJMoSZ3W2HnaJ37UdEAbiKLHI1nJ9wsmnU2TEGrQacaOaNefTxesD64NEDhw0UBeTiQKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:21:33.019607Z"},"content_sha256":"1c0ed30533e1584cc6adb9881bd252365ac0af1aad4da3ce992f0b9286c9db72","schema_version":"1.0","event_id":"sha256:1c0ed30533e1584cc6adb9881bd252365ac0af1aad4da3ce992f0b9286c9db72"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZQVRXBMCYDODLWS6SA4KHQY24Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoxin Li, Hemanth Venkateswara, Sachin Chhabra","submitted_at":"2025-08-22T23:11:43Z","abstract_excerpt":"Training neural networks with one-hot target labels often results in overconfidence and overfitting. Label smoothing addresses this issue by perturbing the one-hot target labels by adding a uniform probability vector to create a regularized label. Although label smoothing improves the network's generalization ability, it assigns equal importance to all the non-target classes, which destroys the inter-class relationships. In this paper, we propose a novel label regularization training strategy called Label Smoothing++, which assigns non-zero probabilities to non-target classes and accounts for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05307","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/2509.05307/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":"2026-07-05T12:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UjstOObB79+HJ/4cKfeyOIsPWtYgHqQvCRsagdBNXP7YyGuAy8/zBkZYAV5HM4ZRouR6zPfH5unEOO9+X2e3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:21:33.020519Z"},"content_sha256":"d0e93b002fbb3382b27904db18fda8c14fd168281b243c234ac1657f22d67a5b","schema_version":"1.0","event_id":"sha256:d0e93b002fbb3382b27904db18fda8c14fd168281b243c234ac1657f22d67a5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQVRXBMCYDODLWS6SA4KHQY24Q/bundle.json","state_url":"https://pith.science/pith/ZQVRXBMCYDODLWS6SA4KHQY24Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQVRXBMCYDODLWS6SA4KHQY24Q/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":"2026-08-09T08:21:33Z","links":{"resolver":"https://pith.science/pith/ZQVRXBMCYDODLWS6SA4KHQY24Q","bundle":"https://pith.science/pith/ZQVRXBMCYDODLWS6SA4KHQY24Q/bundle.json","state":"https://pith.science/pith/ZQVRXBMCYDODLWS6SA4KHQY24Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQVRXBMCYDODLWS6SA4KHQY24Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZQVRXBMCYDODLWS6SA4KHQY24Q","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":"d7bdafb81f22a1a0700f05c57604936edae07b52df3129c72dc8301524b2245a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-22T23:11:43Z","title_canon_sha256":"04c422e7c5e48cdd80abe13fb6ef022a02bf3cb64a31e9b107bcb0350ccb81f1"},"schema_version":"1.0","source":{"id":"2509.05307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05307","created_at":"2026-07-05T12:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05307v1","created_at":"2026-07-05T12:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05307","created_at":"2026-07-05T12:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZQVRXBMCYDOD","created_at":"2026-07-05T12:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZQVRXBMCYDODLWS6","created_at":"2026-07-05T12:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZQVRXBMC","created_at":"2026-07-05T12:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:d0e93b002fbb3382b27904db18fda8c14fd168281b243c234ac1657f22d67a5b","target":"graph","created_at":"2026-07-05T12:05:44Z","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/2509.05307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training neural networks with one-hot target labels often results in overconfidence and overfitting. Label smoothing addresses this issue by perturbing the one-hot target labels by adding a uniform probability vector to create a regularized label. Although label smoothing improves the network's generalization ability, it assigns equal importance to all the non-target classes, which destroys the inter-class relationships. In this paper, we propose a novel label regularization training strategy called Label Smoothing++, which assigns non-zero probabilities to non-target classes and accounts for ","authors_text":"Baoxin Li, Hemanth Venkateswara, Sachin Chhabra","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-22T23:11:43Z","title":"Label Smoothing++: Enhanced Label Regularization for Training Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05307","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":"sha256:1c0ed30533e1584cc6adb9881bd252365ac0af1aad4da3ce992f0b9286c9db72","target":"record","created_at":"2026-07-05T12:05:44Z","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":"d7bdafb81f22a1a0700f05c57604936edae07b52df3129c72dc8301524b2245a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-22T23:11:43Z","title_canon_sha256":"04c422e7c5e48cdd80abe13fb6ef022a02bf3cb64a31e9b107bcb0350ccb81f1"},"schema_version":"1.0","source":{"id":"2509.05307","kind":"arxiv","version":1}},"canonical_sha256":"cc2b1b8582c0dc35da5e9038a3c31ae434c9d6c45b92346135c549ffabf91fdd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc2b1b8582c0dc35da5e9038a3c31ae434c9d6c45b92346135c549ffabf91fdd","first_computed_at":"2026-07-05T12:05:44.695064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:44.695064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SEbiboDzC4IphgEXclIZYP/4giIZHg85OV4DdAIX9hkZsAqTglY8AlrOjqgWPchvlNnKprgkH/A/EzNh7MaMAg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:44.695575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c0ed30533e1584cc6adb9881bd252365ac0af1aad4da3ce992f0b9286c9db72","sha256:d0e93b002fbb3382b27904db18fda8c14fd168281b243c234ac1657f22d67a5b"],"state_sha256":"fa35c91ce44d8c1c0581056a442e15aed12b819389ba1b784313fc734b07141d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gaLT5uo7iUDZ4I5vXaxD2qB3jjLHllxqg0Iq+6mfIpKEMFlytch2YxQemo8umtW2VkfqDpl/RqpzUMLLFrkDCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:21:33.027784Z","bundle_sha256":"8c833d7e1ddca8ba1d9a541361a7b3dc5d4140b77acc0c3eb65cc69d8b3c18b5"}}