{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6HK2VLO2GFJQR3VIGHC42D6X72","short_pith_number":"pith:6HK2VLO2","canonical_record":{"source":{"id":"1803.11364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-30T06:53:40Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"24fff5408100f17edab70b47761aa519b256a73c98880e4c79a697f5a68b2f67","abstract_canon_sha256":"bcb6e1cc59db45db39df8df54b6931a565770cf474737b546d21059514e9a030"},"schema_version":"1.0"},"canonical_sha256":"f1d5aaadda315308eea831c5cd0fd7fe8d082fa237db607adf5959392b9cca44","source":{"kind":"arxiv","id":"1803.11364","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.11364","created_at":"2026-05-17T23:48:06Z"},{"alias_kind":"arxiv_version","alias_value":"1803.11364v1","created_at":"2026-05-17T23:48:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11364","created_at":"2026-05-17T23:48:06Z"},{"alias_kind":"pith_short_12","alias_value":"6HK2VLO2GFJQ","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6HK2VLO2GFJQR3VI","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6HK2VLO2","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6HK2VLO2GFJQR3VIGHC42D6X72","target":"record","payload":{"canonical_record":{"source":{"id":"1803.11364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-30T06:53:40Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"24fff5408100f17edab70b47761aa519b256a73c98880e4c79a697f5a68b2f67","abstract_canon_sha256":"bcb6e1cc59db45db39df8df54b6931a565770cf474737b546d21059514e9a030"},"schema_version":"1.0"},"canonical_sha256":"f1d5aaadda315308eea831c5cd0fd7fe8d082fa237db607adf5959392b9cca44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:06.740483Z","signature_b64":"inpN9TASMi4Mes7zgefxHmPwlIqpCQewAdlaKgZJl0RYlgwrK02+pMDYjdocmn3ER8J3UmgWnNi25Z3UlveQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1d5aaadda315308eea831c5cd0fd7fe8d082fa237db607adf5959392b9cca44","last_reissued_at":"2026-05-17T23:48:06.740015Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:06.740015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.11364","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":"2026-05-17T23:48:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8mgSHZaepNZ/wrZ0uJAT8MbdXUFFKG2rlNlyPxEeiJHRGtMcI6hkZ4FvytlB6vaTYXCtOGYI6fGjaoOQpfXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:37:07.267650Z"},"content_sha256":"8af66de3842057602ac1498c4f5fa353c134f48dafc5684896098ef223833fd1","schema_version":"1.0","event_id":"sha256:8af66de3842057602ac1498c4f5fa353c134f48dafc5684896098ef223833fd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6HK2VLO2GFJQR3VIGHC42D6X72","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Optimization Framework for Learning with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Daiki Ikami, Daiki Tanaka, Kiyoharu Aizawa, Toshihiko Yamasaki","submitted_at":"2018-03-30T06:53:40Z","abstract_excerpt":"Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy labels. Training on such noisy labeled datasets causes performance degradation because DNNs easily overfit to noisy labels. To overcome this problem, we propose a joint optimization framework of learning DNN parameters and estimating true labels. Our framework can correct labels during training by alternating update of network parameters and label"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11364","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":"2026-05-17T23:48:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rlJbtVp058kJ+m7hLnKQI+1DAorqhHDj/F9wyezGmW14frPfTnXtf14uNNn3cpcMpGdW/QI7CEq4FgZ3TjKqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:37:07.268368Z"},"content_sha256":"da797a3cadd1c6c8e6c9a6637c157b159a0dc26b99fb614fd075ee3d6e261a43","schema_version":"1.0","event_id":"sha256:da797a3cadd1c6c8e6c9a6637c157b159a0dc26b99fb614fd075ee3d6e261a43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6HK2VLO2GFJQR3VIGHC42D6X72/bundle.json","state_url":"https://pith.science/pith/6HK2VLO2GFJQR3VIGHC42D6X72/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6HK2VLO2GFJQR3VIGHC42D6X72/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":"2026-05-25T23:37:07Z","links":{"resolver":"https://pith.science/pith/6HK2VLO2GFJQR3VIGHC42D6X72","bundle":"https://pith.science/pith/6HK2VLO2GFJQR3VIGHC42D6X72/bundle.json","state":"https://pith.science/pith/6HK2VLO2GFJQR3VIGHC42D6X72/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6HK2VLO2GFJQR3VIGHC42D6X72/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6HK2VLO2GFJQR3VIGHC42D6X72","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":"bcb6e1cc59db45db39df8df54b6931a565770cf474737b546d21059514e9a030","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-30T06:53:40Z","title_canon_sha256":"24fff5408100f17edab70b47761aa519b256a73c98880e4c79a697f5a68b2f67"},"schema_version":"1.0","source":{"id":"1803.11364","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.11364","created_at":"2026-05-17T23:48:06Z"},{"alias_kind":"arxiv_version","alias_value":"1803.11364v1","created_at":"2026-05-17T23:48:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11364","created_at":"2026-05-17T23:48:06Z"},{"alias_kind":"pith_short_12","alias_value":"6HK2VLO2GFJQ","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6HK2VLO2GFJQR3VI","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6HK2VLO2","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:da797a3cadd1c6c8e6c9a6637c157b159a0dc26b99fb614fd075ee3d6e261a43","target":"graph","created_at":"2026-05-17T23:48:06Z","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":"Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy labels. Training on such noisy labeled datasets causes performance degradation because DNNs easily overfit to noisy labels. To overcome this problem, we propose a joint optimization framework of learning DNN parameters and estimating true labels. Our framework can correct labels during training by alternating update of network parameters and label","authors_text":"Daiki Ikami, Daiki Tanaka, Kiyoharu Aizawa, Toshihiko Yamasaki","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-30T06:53:40Z","title":"Joint Optimization Framework for Learning with Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11364","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":"sha256:8af66de3842057602ac1498c4f5fa353c134f48dafc5684896098ef223833fd1","target":"record","created_at":"2026-05-17T23:48:06Z","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":"bcb6e1cc59db45db39df8df54b6931a565770cf474737b546d21059514e9a030","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-30T06:53:40Z","title_canon_sha256":"24fff5408100f17edab70b47761aa519b256a73c98880e4c79a697f5a68b2f67"},"schema_version":"1.0","source":{"id":"1803.11364","kind":"arxiv","version":1}},"canonical_sha256":"f1d5aaadda315308eea831c5cd0fd7fe8d082fa237db607adf5959392b9cca44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1d5aaadda315308eea831c5cd0fd7fe8d082fa237db607adf5959392b9cca44","first_computed_at":"2026-05-17T23:48:06.740015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:06.740015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"inpN9TASMi4Mes7zgefxHmPwlIqpCQewAdlaKgZJl0RYlgwrK02+pMDYjdocmn3ER8J3UmgWnNi25Z3UlveQDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:06.740483Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.11364","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8af66de3842057602ac1498c4f5fa353c134f48dafc5684896098ef223833fd1","sha256:da797a3cadd1c6c8e6c9a6637c157b159a0dc26b99fb614fd075ee3d6e261a43"],"state_sha256":"adfbca678fc81c02557ec59419cfa578792368b3a13a9a059948ae26f080c1d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qBBupSGha+VYvT2Ywv+9yhJtoVIOiZH13z2JOVpKGGCPMmmNhrvVBZerPy6ERn4WaDqYnjtBXI8oXCtCGwz6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:37:07.271659Z","bundle_sha256":"67703ae42d6ee1fae15f718a67930da1ed7e9c9accf1f9657acc245212b8555b"}}