{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5QSDV3MNIRMZLNMAVR626FQA3E","short_pith_number":"pith:5QSDV3MN","canonical_record":{"source":{"id":"2508.02387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T13:10:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fe3f4a9eab5027caadf27892fc8644064753292b37bb3752fdc502e6361cc0e1","abstract_canon_sha256":"5fef6150d146b7abeaaf0018b4728786f4ff211c1cf7a04bd7c69c98bb87d368"},"schema_version":"1.0"},"canonical_sha256":"ec243aed8d445995b580ac7daf1600d90d2b007133cbab1a3367b0fb9898d076","source":{"kind":"arxiv","id":"2508.02387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02387","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02387v1","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02387","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"5QSDV3MNIRMZ","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"pith_short_16","alias_value":"5QSDV3MNIRMZLNMA","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"pith_short_8","alias_value":"5QSDV3MN","created_at":"2026-07-05T11:48:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5QSDV3MNIRMZLNMAVR626FQA3E","target":"record","payload":{"canonical_record":{"source":{"id":"2508.02387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T13:10:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fe3f4a9eab5027caadf27892fc8644064753292b37bb3752fdc502e6361cc0e1","abstract_canon_sha256":"5fef6150d146b7abeaaf0018b4728786f4ff211c1cf7a04bd7c69c98bb87d368"},"schema_version":"1.0"},"canonical_sha256":"ec243aed8d445995b580ac7daf1600d90d2b007133cbab1a3367b0fb9898d076","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:13.448667Z","signature_b64":"YTIYTrIVrcUD5raU4srOSZzNuf8eYqAF4+KOmDd3o/HFzPaXYhXNDVCJL7QyVruBrjMARBOdgpH9WF4uHxJlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec243aed8d445995b580ac7daf1600d90d2b007133cbab1a3367b0fb9898d076","last_reissued_at":"2026-07-05T11:48:13.448182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:13.448182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.02387","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":"2026-07-05T11:48:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sSNNbEB9EoR1AzBFYTRlEuBlyik/bHaLM2OSV7Yn9/xuMYg6NHlDBwFDSX6/sdE5JtCpBIs7eA4nntj29RaGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:51:41.504512Z"},"content_sha256":"ed4c301c97b7d1024e507588be9272a5ca6112f8bdce6324b43276f9ea5c7549","schema_version":"1.0","event_id":"sha256:ed4c301c97b7d1024e507588be9272a5ca6112f8bdce6324b43276f9ea5c7549"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5QSDV3MNIRMZLNMAVR626FQA3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"$\\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Deming Zhai, Jialiang Wang, Junjun Jiang, Xiangyang Ji, Xianming Liu, Xiong Zhou","submitted_at":"2025-08-04T13:10:48Z","abstract_excerpt":"Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise tolerance in the presence of label noise, particularly symmetric losses. However, they usually suffer from the underfitting issue due to the overly strict symmetric condition. In this work, we propose a simple yet effective approach for relaxing the symmetric condition, namely $\\epsilon$-softmax, which simply modifies the outputs of the softmax layer to approximate one-hot vectors with a controllable error $\\epsilon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02387","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/2508.02387/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":"2026-07-05T11:48:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QrrcgepEbCvvFivsQ+tJ7WjKnNWbywvb6iwFzRmMXc6cgj4qH9bciYMO6dTVcC7Pd98ZuRZ9uRlyoQDW5MtDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:51:41.505046Z"},"content_sha256":"16cda14f6833a57577cbe01566d89b8a3da2b37968280676a8c77aa693ffa2a4","schema_version":"1.0","event_id":"sha256:16cda14f6833a57577cbe01566d89b8a3da2b37968280676a8c77aa693ffa2a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5QSDV3MNIRMZLNMAVR626FQA3E/bundle.json","state_url":"https://pith.science/pith/5QSDV3MNIRMZLNMAVR626FQA3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5QSDV3MNIRMZLNMAVR626FQA3E/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":"2026-08-08T12:51:41Z","links":{"resolver":"https://pith.science/pith/5QSDV3MNIRMZLNMAVR626FQA3E","bundle":"https://pith.science/pith/5QSDV3MNIRMZLNMAVR626FQA3E/bundle.json","state":"https://pith.science/pith/5QSDV3MNIRMZLNMAVR626FQA3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5QSDV3MNIRMZLNMAVR626FQA3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5QSDV3MNIRMZLNMAVR626FQA3E","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":"5fef6150d146b7abeaaf0018b4728786f4ff211c1cf7a04bd7c69c98bb87d368","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T13:10:48Z","title_canon_sha256":"fe3f4a9eab5027caadf27892fc8644064753292b37bb3752fdc502e6361cc0e1"},"schema_version":"1.0","source":{"id":"2508.02387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02387","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02387v1","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02387","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"5QSDV3MNIRMZ","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"pith_short_16","alias_value":"5QSDV3MNIRMZLNMA","created_at":"2026-07-05T11:48:13Z"},{"alias_kind":"pith_short_8","alias_value":"5QSDV3MN","created_at":"2026-07-05T11:48:13Z"}],"graph_snapshots":[{"event_id":"sha256:16cda14f6833a57577cbe01566d89b8a3da2b37968280676a8c77aa693ffa2a4","target":"graph","created_at":"2026-07-05T11:48:13Z","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/2508.02387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise tolerance in the presence of label noise, particularly symmetric losses. However, they usually suffer from the underfitting issue due to the overly strict symmetric condition. In this work, we propose a simple yet effective approach for relaxing the symmetric condition, namely $\\epsilon$-softmax, which simply modifies the outputs of the softmax layer to approximate one-hot vectors with a controllable error $\\epsilon","authors_text":"Deming Zhai, Jialiang Wang, Junjun Jiang, Xiangyang Ji, Xianming Liu, Xiong Zhou","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T13:10:48Z","title":"$\\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02387","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:ed4c301c97b7d1024e507588be9272a5ca6112f8bdce6324b43276f9ea5c7549","target":"record","created_at":"2026-07-05T11:48:13Z","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":"5fef6150d146b7abeaaf0018b4728786f4ff211c1cf7a04bd7c69c98bb87d368","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T13:10:48Z","title_canon_sha256":"fe3f4a9eab5027caadf27892fc8644064753292b37bb3752fdc502e6361cc0e1"},"schema_version":"1.0","source":{"id":"2508.02387","kind":"arxiv","version":1}},"canonical_sha256":"ec243aed8d445995b580ac7daf1600d90d2b007133cbab1a3367b0fb9898d076","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec243aed8d445995b580ac7daf1600d90d2b007133cbab1a3367b0fb9898d076","first_computed_at":"2026-07-05T11:48:13.448182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:13.448182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YTIYTrIVrcUD5raU4srOSZzNuf8eYqAF4+KOmDd3o/HFzPaXYhXNDVCJL7QyVruBrjMARBOdgpH9WF4uHxJlBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:13.448667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed4c301c97b7d1024e507588be9272a5ca6112f8bdce6324b43276f9ea5c7549","sha256:16cda14f6833a57577cbe01566d89b8a3da2b37968280676a8c77aa693ffa2a4"],"state_sha256":"8c1991629879cade369dba6f52722351f01372868ce2072fe90aafe5c1fdd4e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybDtsKyPTPLfAhqwmvhGhd8QC6g8WlYTMd2R2ebAkNW/GM8W1KyHcfJwwf1D75Iapq1QuPEgrvgBpZm+Q5qsAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:51:41.509816Z","bundle_sha256":"e3f2309eb955dacc3cdbdf9bd4b02b937b7af2dc6d87f0ce14ce5cb23d91451d"}}