{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TO7LRN3KGOTHKMBP7WJZ5LNXJF","short_pith_number":"pith:TO7LRN3K","canonical_record":{"source":{"id":"2007.05305","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-10T11:12:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ea0a7efd0e45dee7d2d8836e8a0af9ae1cee64e96a58742c33ee2e568ead3130","abstract_canon_sha256":"aa04a2a432d6abda969fec54bae06db5562330bd583f61e3777904cbf8c6b0fc"},"schema_version":"1.0"},"canonical_sha256":"9bbeb8b76a33a675302ffd939eadb7495d77033a838cec8884bfbf560fa0441c","source":{"kind":"arxiv","id":"2007.05305","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.05305","created_at":"2026-07-05T01:18:05Z"},{"alias_kind":"arxiv_version","alias_value":"2007.05305v2","created_at":"2026-07-05T01:18:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.05305","created_at":"2026-07-05T01:18:05Z"},{"alias_kind":"pith_short_12","alias_value":"TO7LRN3KGOTH","created_at":"2026-07-05T01:18:05Z"},{"alias_kind":"pith_short_16","alias_value":"TO7LRN3KGOTHKMBP","created_at":"2026-07-05T01:18:05Z"},{"alias_kind":"pith_short_8","alias_value":"TO7LRN3K","created_at":"2026-07-05T01:18:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TO7LRN3KGOTHKMBP7WJZ5LNXJF","target":"record","payload":{"canonical_record":{"source":{"id":"2007.05305","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-10T11:12:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ea0a7efd0e45dee7d2d8836e8a0af9ae1cee64e96a58742c33ee2e568ead3130","abstract_canon_sha256":"aa04a2a432d6abda969fec54bae06db5562330bd583f61e3777904cbf8c6b0fc"},"schema_version":"1.0"},"canonical_sha256":"9bbeb8b76a33a675302ffd939eadb7495d77033a838cec8884bfbf560fa0441c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:05.255876Z","signature_b64":"g7Eu06/F03j8XDcLJcRLeY2r6A2Dm8LJyAVHwG1wpoaZCOXbasRMeugUc94QRDXAf9P4AWXvwYKvR3LE4Ry8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bbeb8b76a33a675302ffd939eadb7495d77033a838cec8884bfbf560fa0441c","last_reissued_at":"2026-07-05T01:18:05.255471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:05.255471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.05305","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:18:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IJOdgxr177QvYwchWE9AVhzspUmLZHufqi1cMwmv5yN42DSzjHE2IO1NYvABWA3e0WC7zHHuPqIYw+vOCA7RDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T16:09:16.626697Z"},"content_sha256":"90b51cd85c3d6c0887816fd50fde0b02ff9b358214208f52bdb04f1385ac28bc","schema_version":"1.0","event_id":"sha256:90b51cd85c3d6c0887816fd50fde0b02ff9b358214208f52bdb04f1385ac28bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TO7LRN3KGOTHKMBP7WJZ5LNXJF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ExpertNet: Adversarial Learning and Recovery Against Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amirmasoud Ghiassi, Lydia Y.Chen, Robert Birke, Rui Han","submitted_at":"2020-07-10T11:12:16Z","abstract_excerpt":"Today's available datasets in the wild, e.g., from social media and open platforms, present tremendous opportunities and challenges for deep learning, as there is a significant portion of tagged images, but often with noisy, i.e. erroneous, labels. Recent studies improve the robustness of deep models against noisy labels without the knowledge of true labels. In this paper, we advocate to derive a stronger classifier which proactively makes use of the noisy labels in addition to the original images - turning noisy labels into learning features. To such an end, we propose a novel framework, Expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.05305","kind":"arxiv","version":2},"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/2007.05305/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":"2026-07-05T01:18:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LobflWemioCrF4jraY/MT3Tockh2vvPv5Xpf0N1W1nOumiGOVvevv321R3YdZLhvrfumf5XyFi0DWoefSXZaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T16:09:16.627066Z"},"content_sha256":"17d9f44eee8030b6cc5ca9e8ecc2912689b3c0affe36509ae7d5e08c448b26e6","schema_version":"1.0","event_id":"sha256:17d9f44eee8030b6cc5ca9e8ecc2912689b3c0affe36509ae7d5e08c448b26e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TO7LRN3KGOTHKMBP7WJZ5LNXJF/bundle.json","state_url":"https://pith.science/pith/TO7LRN3KGOTHKMBP7WJZ5LNXJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TO7LRN3KGOTHKMBP7WJZ5LNXJF/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":"2026-07-12T16:09:16Z","links":{"resolver":"https://pith.science/pith/TO7LRN3KGOTHKMBP7WJZ5LNXJF","bundle":"https://pith.science/pith/TO7LRN3KGOTHKMBP7WJZ5LNXJF/bundle.json","state":"https://pith.science/pith/TO7LRN3KGOTHKMBP7WJZ5LNXJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TO7LRN3KGOTHKMBP7WJZ5LNXJF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TO7LRN3KGOTHKMBP7WJZ5LNXJF","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":"aa04a2a432d6abda969fec54bae06db5562330bd583f61e3777904cbf8c6b0fc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-10T11:12:16Z","title_canon_sha256":"ea0a7efd0e45dee7d2d8836e8a0af9ae1cee64e96a58742c33ee2e568ead3130"},"schema_version":"1.0","source":{"id":"2007.05305","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.05305","created_at":"2026-07-05T01:18:05Z"},{"alias_kind":"arxiv_version","alias_value":"2007.05305v2","created_at":"2026-07-05T01:18:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.05305","created_at":"2026-07-05T01:18:05Z"},{"alias_kind":"pith_short_12","alias_value":"TO7LRN3KGOTH","created_at":"2026-07-05T01:18:05Z"},{"alias_kind":"pith_short_16","alias_value":"TO7LRN3KGOTHKMBP","created_at":"2026-07-05T01:18:05Z"},{"alias_kind":"pith_short_8","alias_value":"TO7LRN3K","created_at":"2026-07-05T01:18:05Z"}],"graph_snapshots":[{"event_id":"sha256:17d9f44eee8030b6cc5ca9e8ecc2912689b3c0affe36509ae7d5e08c448b26e6","target":"graph","created_at":"2026-07-05T01:18:05Z","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/2007.05305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Today's available datasets in the wild, e.g., from social media and open platforms, present tremendous opportunities and challenges for deep learning, as there is a significant portion of tagged images, but often with noisy, i.e. erroneous, labels. Recent studies improve the robustness of deep models against noisy labels without the knowledge of true labels. In this paper, we advocate to derive a stronger classifier which proactively makes use of the noisy labels in addition to the original images - turning noisy labels into learning features. To such an end, we propose a novel framework, Expe","authors_text":"Amirmasoud Ghiassi, Lydia Y.Chen, Robert Birke, Rui Han","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-10T11:12:16Z","title":"ExpertNet: Adversarial Learning and Recovery Against Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.05305","kind":"arxiv","version":2},"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":"sha256:90b51cd85c3d6c0887816fd50fde0b02ff9b358214208f52bdb04f1385ac28bc","target":"record","created_at":"2026-07-05T01:18:05Z","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":"aa04a2a432d6abda969fec54bae06db5562330bd583f61e3777904cbf8c6b0fc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-10T11:12:16Z","title_canon_sha256":"ea0a7efd0e45dee7d2d8836e8a0af9ae1cee64e96a58742c33ee2e568ead3130"},"schema_version":"1.0","source":{"id":"2007.05305","kind":"arxiv","version":2}},"canonical_sha256":"9bbeb8b76a33a675302ffd939eadb7495d77033a838cec8884bfbf560fa0441c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bbeb8b76a33a675302ffd939eadb7495d77033a838cec8884bfbf560fa0441c","first_computed_at":"2026-07-05T01:18:05.255471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:18:05.255471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g7Eu06/F03j8XDcLJcRLeY2r6A2Dm8LJyAVHwG1wpoaZCOXbasRMeugUc94QRDXAf9P4AWXvwYKvR3LE4Ry8AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:18:05.255876Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.05305","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90b51cd85c3d6c0887816fd50fde0b02ff9b358214208f52bdb04f1385ac28bc","sha256:17d9f44eee8030b6cc5ca9e8ecc2912689b3c0affe36509ae7d5e08c448b26e6"],"state_sha256":"f9a4f25d295e7a3250e134f9296bb54b101bc736f02a16e3a4320b4382f87c8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xkcbk9WReiL634cNrP5OYjs3dDUNqWZg7bHaEpkIc20gKbJqBKmldGUrQpCcKiBvms1wzk5y/Gq4DR955aJvDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T16:09:16.629142Z","bundle_sha256":"aeb824d479886de7ba83a361e0433f96bb81cfe67527591b06c17ff5e5f4331a"}}