{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IOMPCY57MS7ONUS4F3GQIHIUNJ","short_pith_number":"pith:IOMPCY57","canonical_record":{"source":{"id":"2103.03414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-05T01:17:04Z","cross_cats_sorted":[],"title_canon_sha256":"f4fd6565b375a777be825611dc9f675c1db8f9520d288801e5db7fa2df070587","abstract_canon_sha256":"ed2a907d0c36b4be0218b408ae0ee0b918e278471b6c5a14db4382ee3db484ce"},"schema_version":"1.0"},"canonical_sha256":"4398f163bf64bee6d25c2ecd041d146a5a85d4cf51aa69bd6f3f749f1366a1b8","source":{"kind":"arxiv","id":"2103.03414","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03414","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03414v1","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03414","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"pith_short_12","alias_value":"IOMPCY57MS7O","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"pith_short_16","alias_value":"IOMPCY57MS7ONUS4","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"pith_short_8","alias_value":"IOMPCY57","created_at":"2026-07-05T02:20:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IOMPCY57MS7ONUS4F3GQIHIUNJ","target":"record","payload":{"canonical_record":{"source":{"id":"2103.03414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-05T01:17:04Z","cross_cats_sorted":[],"title_canon_sha256":"f4fd6565b375a777be825611dc9f675c1db8f9520d288801e5db7fa2df070587","abstract_canon_sha256":"ed2a907d0c36b4be0218b408ae0ee0b918e278471b6c5a14db4382ee3db484ce"},"schema_version":"1.0"},"canonical_sha256":"4398f163bf64bee6d25c2ecd041d146a5a85d4cf51aa69bd6f3f749f1366a1b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:35.010951Z","signature_b64":"QfY6Q0q+uGVQMdpIPVxXmm7JR5EBl9Mahpmy/3yQbcewyNgTdFpn79+NqgK/f/7xXKjirM9A16SF53JnyPyDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4398f163bf64bee6d25c2ecd041d146a5a85d4cf51aa69bd6f3f749f1366a1b8","last_reissued_at":"2026-07-05T02:20:35.010481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:35.010481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.03414","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":"2026-07-05T02:20:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOr6jCLyH2gN9gyLFdx6hlDAvjTvxB7vVT3LfePnmQeGUUWRN2GrpOZ8q2rfe4Lc/+CZ8xT6VJQ2lbD+OFmSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:27:23.158868Z"},"content_sha256":"b5f4a96ddff6c114666442282a248343695827017126ec2d0866a907d1fd0e0e","schema_version":"1.0","event_id":"sha256:b5f4a96ddff6c114666442282a248343695827017126ec2d0866a907d1fd0e0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IOMPCY57MS7ONUS4F3GQIHIUNJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Robust Training for Graph NeuralNetworks against Label Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jie Yin, Ling Chen, Yayong Li","submitted_at":"2021-03-05T01:17:04Z","abstract_excerpt":"Graph neural networks (GNNs) have achieved state-of-the-art performance for node classification on graphs. The vast majority of existing works assume that genuine node labels are always provided for training. However, there has been very little research effort on how to improve the robustness of GNNs in the presence of label noise. Learning with label noise has been primarily studied in the context of image classification, but these techniques cannot be directly applied to graph-structured data, due to two major challenges -- label sparsity and label dependency -- faced by learning on graphs. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03414","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/2103.03414/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":"2026-07-05T02:20:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qj5s7/fZYwXcSHe0yWt4nbUGsIc+QVf+hJB+pg1HeKa7pBo/QAJe8nwfHZpHtF0cl2xQCR1rGeOI69NuwnIyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:27:23.159415Z"},"content_sha256":"eb1639cdb00a2ead2f8641173aa362452adb66853ea8fd3a0c121dca809e7fda","schema_version":"1.0","event_id":"sha256:eb1639cdb00a2ead2f8641173aa362452adb66853ea8fd3a0c121dca809e7fda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IOMPCY57MS7ONUS4F3GQIHIUNJ/bundle.json","state_url":"https://pith.science/pith/IOMPCY57MS7ONUS4F3GQIHIUNJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IOMPCY57MS7ONUS4F3GQIHIUNJ/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":"2026-08-03T16:27:23Z","links":{"resolver":"https://pith.science/pith/IOMPCY57MS7ONUS4F3GQIHIUNJ","bundle":"https://pith.science/pith/IOMPCY57MS7ONUS4F3GQIHIUNJ/bundle.json","state":"https://pith.science/pith/IOMPCY57MS7ONUS4F3GQIHIUNJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IOMPCY57MS7ONUS4F3GQIHIUNJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IOMPCY57MS7ONUS4F3GQIHIUNJ","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":"ed2a907d0c36b4be0218b408ae0ee0b918e278471b6c5a14db4382ee3db484ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-05T01:17:04Z","title_canon_sha256":"f4fd6565b375a777be825611dc9f675c1db8f9520d288801e5db7fa2df070587"},"schema_version":"1.0","source":{"id":"2103.03414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03414","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03414v1","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03414","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"pith_short_12","alias_value":"IOMPCY57MS7O","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"pith_short_16","alias_value":"IOMPCY57MS7ONUS4","created_at":"2026-07-05T02:20:35Z"},{"alias_kind":"pith_short_8","alias_value":"IOMPCY57","created_at":"2026-07-05T02:20:35Z"}],"graph_snapshots":[{"event_id":"sha256:eb1639cdb00a2ead2f8641173aa362452adb66853ea8fd3a0c121dca809e7fda","target":"graph","created_at":"2026-07-05T02:20:35Z","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/2103.03414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph neural networks (GNNs) have achieved state-of-the-art performance for node classification on graphs. The vast majority of existing works assume that genuine node labels are always provided for training. However, there has been very little research effort on how to improve the robustness of GNNs in the presence of label noise. Learning with label noise has been primarily studied in the context of image classification, but these techniques cannot be directly applied to graph-structured data, due to two major challenges -- label sparsity and label dependency -- faced by learning on graphs. ","authors_text":"Jie Yin, Ling Chen, Yayong Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-05T01:17:04Z","title":"Unified Robust Training for Graph NeuralNetworks against Label Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03414","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:b5f4a96ddff6c114666442282a248343695827017126ec2d0866a907d1fd0e0e","target":"record","created_at":"2026-07-05T02:20:35Z","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":"ed2a907d0c36b4be0218b408ae0ee0b918e278471b6c5a14db4382ee3db484ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-05T01:17:04Z","title_canon_sha256":"f4fd6565b375a777be825611dc9f675c1db8f9520d288801e5db7fa2df070587"},"schema_version":"1.0","source":{"id":"2103.03414","kind":"arxiv","version":1}},"canonical_sha256":"4398f163bf64bee6d25c2ecd041d146a5a85d4cf51aa69bd6f3f749f1366a1b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4398f163bf64bee6d25c2ecd041d146a5a85d4cf51aa69bd6f3f749f1366a1b8","first_computed_at":"2026-07-05T02:20:35.010481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:35.010481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QfY6Q0q+uGVQMdpIPVxXmm7JR5EBl9Mahpmy/3yQbcewyNgTdFpn79+NqgK/f/7xXKjirM9A16SF53JnyPyDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:35.010951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.03414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5f4a96ddff6c114666442282a248343695827017126ec2d0866a907d1fd0e0e","sha256:eb1639cdb00a2ead2f8641173aa362452adb66853ea8fd3a0c121dca809e7fda"],"state_sha256":"2d2bc24038457deaa59cb5757b2b9ea32c4fd0fe05f73c49537d7394aaa9d656"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3R4POaTZPfXFwHDDuqevXDsPkv6r7vM9eAJ4nME3dbEiKOm6b45pY6/Cg4xY/II9C3U5+1GCMSvhhMZKvOJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:27:23.162783Z","bundle_sha256":"9a2cbabfd2a68f34b08b6b64eb3e993c8bc8e03452f1ba54ae1ba5649734eb07"}}