{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2PLC2XMQ3ZLK2ISAT6PHNAJRXH","short_pith_number":"pith:2PLC2XMQ","canonical_record":{"source":{"id":"2002.07394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-18T06:20:06Z","cross_cats_sorted":[],"title_canon_sha256":"b4f529fa9d8bd36503795f7cec3f164d5c40e975516d3c48f9c4c48c50b9e1e5","abstract_canon_sha256":"86787e0cdd01ca3d3125c36c4cea4781572422e06faa88c4d57008d614bc7dce"},"schema_version":"1.0"},"canonical_sha256":"d3d62d5d90de56ad22409f9e768131b9ffb032da256e163cc531d0ec6247ab2e","source":{"kind":"arxiv","id":"2002.07394","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.07394","created_at":"2026-07-05T00:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"2002.07394v1","created_at":"2026-07-05T00:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07394","created_at":"2026-07-05T00:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"2PLC2XMQ3ZLK","created_at":"2026-07-05T00:42:24Z"},{"alias_kind":"pith_short_16","alias_value":"2PLC2XMQ3ZLK2ISA","created_at":"2026-07-05T00:42:24Z"},{"alias_kind":"pith_short_8","alias_value":"2PLC2XMQ","created_at":"2026-07-05T00:42:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2PLC2XMQ3ZLK2ISAT6PHNAJRXH","target":"record","payload":{"canonical_record":{"source":{"id":"2002.07394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-18T06:20:06Z","cross_cats_sorted":[],"title_canon_sha256":"b4f529fa9d8bd36503795f7cec3f164d5c40e975516d3c48f9c4c48c50b9e1e5","abstract_canon_sha256":"86787e0cdd01ca3d3125c36c4cea4781572422e06faa88c4d57008d614bc7dce"},"schema_version":"1.0"},"canonical_sha256":"d3d62d5d90de56ad22409f9e768131b9ffb032da256e163cc531d0ec6247ab2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:24.081706Z","signature_b64":"pAfMpicn4hKtKe+rEnRIZYMPLyrnGz2VzP9M54aGoAeNJy3tJ8Yoz05iVkXKzKf/9ciQVkKD5JPmCs6ceYAGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3d62d5d90de56ad22409f9e768131b9ffb032da256e163cc531d0ec6247ab2e","last_reissued_at":"2026-07-05T00:42:24.081208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:24.081208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.07394","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":"2026-07-05T00:42:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x/x9Y4iwP3+TUlTB/ESN7Y25b7fJSBx3N+xQ5jJjDqqmKQ07IXXnZC9PUGF7qYLfDiD0Blzkx+L5oZd7ydSrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T12:30:38.128907Z"},"content_sha256":"dfbf2e1842ff296b67e345ec2804ac506185bb190bdac303204aa0786ca8dfcc","schema_version":"1.0","event_id":"sha256:dfbf2e1842ff296b67e345ec2804ac506185bb190bdac303204aa0786ca8dfcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2PLC2XMQ3ZLK2ISAT6PHNAJRXH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junnan Li, Richard Socher, Steven C.H. Hoi","submitted_at":"2020-02-18T06:20:06Z","abstract_excerpt":"Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by exploiting unlabeled data. In this work, we propose DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques. In particular, DivideMix models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07394","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/2002.07394/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":"2026-07-05T00:42:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQCmgEeeDHMRDOPBYqStexiOJNhEb64vXjeXzFbZM6X3obpr88GVhbOCN/sftHMo6FWOvcnMULWme7XG9CH4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T12:30:38.129269Z"},"content_sha256":"fac7c5fd4f6fbd479f3bf6822dfac54b989a10b34b2f472a5b9cb032ab43b7b2","schema_version":"1.0","event_id":"sha256:fac7c5fd4f6fbd479f3bf6822dfac54b989a10b34b2f472a5b9cb032ab43b7b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/bundle.json","state_url":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/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":"2026-07-18T12:30:38Z","links":{"resolver":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH","bundle":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/bundle.json","state":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2PLC2XMQ3ZLK2ISAT6PHNAJRXH","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":"86787e0cdd01ca3d3125c36c4cea4781572422e06faa88c4d57008d614bc7dce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-18T06:20:06Z","title_canon_sha256":"b4f529fa9d8bd36503795f7cec3f164d5c40e975516d3c48f9c4c48c50b9e1e5"},"schema_version":"1.0","source":{"id":"2002.07394","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.07394","created_at":"2026-07-05T00:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"2002.07394v1","created_at":"2026-07-05T00:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07394","created_at":"2026-07-05T00:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"2PLC2XMQ3ZLK","created_at":"2026-07-05T00:42:24Z"},{"alias_kind":"pith_short_16","alias_value":"2PLC2XMQ3ZLK2ISA","created_at":"2026-07-05T00:42:24Z"},{"alias_kind":"pith_short_8","alias_value":"2PLC2XMQ","created_at":"2026-07-05T00:42:24Z"}],"graph_snapshots":[{"event_id":"sha256:fac7c5fd4f6fbd479f3bf6822dfac54b989a10b34b2f472a5b9cb032ab43b7b2","target":"graph","created_at":"2026-07-05T00:42:24Z","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/2002.07394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by exploiting unlabeled data. In this work, we propose DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques. In particular, DivideMix models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set wit","authors_text":"Junnan Li, Richard Socher, Steven C.H. Hoi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-18T06:20:06Z","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07394","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:dfbf2e1842ff296b67e345ec2804ac506185bb190bdac303204aa0786ca8dfcc","target":"record","created_at":"2026-07-05T00:42:24Z","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":"86787e0cdd01ca3d3125c36c4cea4781572422e06faa88c4d57008d614bc7dce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-18T06:20:06Z","title_canon_sha256":"b4f529fa9d8bd36503795f7cec3f164d5c40e975516d3c48f9c4c48c50b9e1e5"},"schema_version":"1.0","source":{"id":"2002.07394","kind":"arxiv","version":1}},"canonical_sha256":"d3d62d5d90de56ad22409f9e768131b9ffb032da256e163cc531d0ec6247ab2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3d62d5d90de56ad22409f9e768131b9ffb032da256e163cc531d0ec6247ab2e","first_computed_at":"2026-07-05T00:42:24.081208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:42:24.081208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pAfMpicn4hKtKe+rEnRIZYMPLyrnGz2VzP9M54aGoAeNJy3tJ8Yoz05iVkXKzKf/9ciQVkKD5JPmCs6ceYAGDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:42:24.081706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.07394","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfbf2e1842ff296b67e345ec2804ac506185bb190bdac303204aa0786ca8dfcc","sha256:fac7c5fd4f6fbd479f3bf6822dfac54b989a10b34b2f472a5b9cb032ab43b7b2"],"state_sha256":"07a506b00431402f755786762f9d89b63b3bacd6df0e52da7badc955e8c3e509"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6soL08mU/r8DB06Yegn4qKuZAyyHBbggY3f1GlXYrURTB9TMhfchPFi16dLg4H+u9jlGC4vLcW6lmS0hbe9uDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T12:30:38.131340Z","bundle_sha256":"906b1b79e28e3fb5622b38632604925d3f5a730197da0845c927619a3b4e6277"}}