{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:F3LQEMU7DNREK2D7WOG727JQ6L","short_pith_number":"pith:F3LQEMU7","canonical_record":{"source":{"id":"1906.05509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T06:56:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4aca80627d4e1f4b1bf6a325845335d63470b0d179b660f8901540cf1082cde6","abstract_canon_sha256":"df1351f3d08d2609a509e8da2de3e46cc4b21978dd455e2bd51fc03c3e865240"},"schema_version":"1.0"},"canonical_sha256":"2ed702329f1b6245687fb38dfd7d30f2c442ff8913581bb9549a0a4e43e9fad0","source":{"kind":"arxiv","id":"1906.05509","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05509","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05509v1","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05509","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"F3LQEMU7DNRE","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"F3LQEMU7DNREK2D7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"F3LQEMU7","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:F3LQEMU7DNREK2D7WOG727JQ6L","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T06:56:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4aca80627d4e1f4b1bf6a325845335d63470b0d179b660f8901540cf1082cde6","abstract_canon_sha256":"df1351f3d08d2609a509e8da2de3e46cc4b21978dd455e2bd51fc03c3e865240"},"schema_version":"1.0"},"canonical_sha256":"2ed702329f1b6245687fb38dfd7d30f2c442ff8913581bb9549a0a4e43e9fad0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:25.188726Z","signature_b64":"tg0v52MU/oNDywZ8m30xyW9k8ZBRJSEvmLlXrp5lQO/k0/Zzb/aC4ZdEod6FOHaB4Hlw1oZpnTNc3za6MNfVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ed702329f1b6245687fb38dfd7d30f2c442ff8913581bb9549a0a4e43e9fad0","last_reissued_at":"2026-05-17T23:43:25.188286Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:25.188286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05509","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":"2026-05-17T23:43:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GIimN34Y37PKcXO8fXKGESPRvZNWwsxy7VXPGjYKM3+SMfAyuGoMz1BYlnY+oT22bRYEIWg51Oq1M9AewP2HAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:57:38.690233Z"},"content_sha256":"4615365a83c02a1b8ffa8c1d1e06b2e411870e8796232aef6e64a3fb9509d02c","schema_version":"1.0","event_id":"sha256:4615365a83c02a1b8ffa8c1d1e06b2e411870e8796232aef6e64a3fb9509d02c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:F3LQEMU7DNREK2D7WOG727JQ6L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benben Liao, Guangyong Chen, Pengfei Chen, Shengyu Zhang","submitted_at":"2019-06-13T06:56:00Z","abstract_excerpt":"Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) since DNNs can easily overfit to the noisy labels. Most recent efforts have been devoted to defending noisy labels by discarding noisy samples from the training set or assigning weights to training samples, where the weight associated with a noisy sample is expected to be small. Thereby, these previous efforts result in a waste of samples, especially those assigned with small weights. The input $x$ is always useful regardless of whether its observed label $y$ is clean. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05509","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":""},"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":"2026-05-17T23:43:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0v56CBfy95m9B0DoPX8r0yE/aD6WBri/1gNZ1V8vbeY8jige6zbj1Gd9YgaD1AdvRCsaBU+xUaQ1QQy2cmmlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:57:38.690880Z"},"content_sha256":"195d9c0f2e67cdc5bd61b5b149500579f8f7c6fdffa4babbae3d9094e04222c1","schema_version":"1.0","event_id":"sha256:195d9c0f2e67cdc5bd61b5b149500579f8f7c6fdffa4babbae3d9094e04222c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3LQEMU7DNREK2D7WOG727JQ6L/bundle.json","state_url":"https://pith.science/pith/F3LQEMU7DNREK2D7WOG727JQ6L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3LQEMU7DNREK2D7WOG727JQ6L/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":"2026-05-26T17:57:38Z","links":{"resolver":"https://pith.science/pith/F3LQEMU7DNREK2D7WOG727JQ6L","bundle":"https://pith.science/pith/F3LQEMU7DNREK2D7WOG727JQ6L/bundle.json","state":"https://pith.science/pith/F3LQEMU7DNREK2D7WOG727JQ6L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3LQEMU7DNREK2D7WOG727JQ6L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:F3LQEMU7DNREK2D7WOG727JQ6L","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":"df1351f3d08d2609a509e8da2de3e46cc4b21978dd455e2bd51fc03c3e865240","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T06:56:00Z","title_canon_sha256":"4aca80627d4e1f4b1bf6a325845335d63470b0d179b660f8901540cf1082cde6"},"schema_version":"1.0","source":{"id":"1906.05509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05509","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05509v1","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05509","created_at":"2026-05-17T23:43:25Z"},{"alias_kind":"pith_short_12","alias_value":"F3LQEMU7DNRE","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"F3LQEMU7DNREK2D7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"F3LQEMU7","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:195d9c0f2e67cdc5bd61b5b149500579f8f7c6fdffa4babbae3d9094e04222c1","target":"graph","created_at":"2026-05-17T23:43:25Z","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"},"paper":{"abstract_excerpt":"Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) since DNNs can easily overfit to the noisy labels. Most recent efforts have been devoted to defending noisy labels by discarding noisy samples from the training set or assigning weights to training samples, where the weight associated with a noisy sample is expected to be small. Thereby, these previous efforts result in a waste of samples, especially those assigned with small weights. The input $x$ is always useful regardless of whether its observed label $y$ is clean. ","authors_text":"Benben Liao, Guangyong Chen, Pengfei Chen, Shengyu Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T06:56:00Z","title":"A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05509","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":"sha256:4615365a83c02a1b8ffa8c1d1e06b2e411870e8796232aef6e64a3fb9509d02c","target":"record","created_at":"2026-05-17T23:43:25Z","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":"df1351f3d08d2609a509e8da2de3e46cc4b21978dd455e2bd51fc03c3e865240","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T06:56:00Z","title_canon_sha256":"4aca80627d4e1f4b1bf6a325845335d63470b0d179b660f8901540cf1082cde6"},"schema_version":"1.0","source":{"id":"1906.05509","kind":"arxiv","version":1}},"canonical_sha256":"2ed702329f1b6245687fb38dfd7d30f2c442ff8913581bb9549a0a4e43e9fad0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ed702329f1b6245687fb38dfd7d30f2c442ff8913581bb9549a0a4e43e9fad0","first_computed_at":"2026-05-17T23:43:25.188286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:25.188286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tg0v52MU/oNDywZ8m30xyW9k8ZBRJSEvmLlXrp5lQO/k0/Zzb/aC4ZdEod6FOHaB4Hlw1oZpnTNc3za6MNfVCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:25.188726Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4615365a83c02a1b8ffa8c1d1e06b2e411870e8796232aef6e64a3fb9509d02c","sha256:195d9c0f2e67cdc5bd61b5b149500579f8f7c6fdffa4babbae3d9094e04222c1"],"state_sha256":"4e47369a048938a9739b1f50435a2be1ea7ccc319412f4e67c05d6d17607aa8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XjC9vw+IpIjOGrL36n0L+cS+LQsX40Bb1Lf3ZPhkEiWlpwh3rIR4wIvc3Ln18+X4Q6TGDdJffrGiCZgQe7dGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:57:38.693876Z","bundle_sha256":"9f95f0bc4c9d79632f118a0c1ebfeea88e7d839c497cced2173ffa8ca88ffe81"}}