{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VYERO7SUNC3UQTKTD5RXNZ2ADB","short_pith_number":"pith:VYERO7SU","canonical_record":{"source":{"id":"2312.08852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T17:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"85a3ad2762fd779874ecafd0f52af6b24f0a266d94bbe3aec81cb024d8c108af","abstract_canon_sha256":"790d3963e6b0a8512d49e589d7d95ea24e83e7a2f66b46eb235c13f1fdb50587"},"schema_version":"1.0"},"canonical_sha256":"ae09177e5468b7484d531f6376e7401872680d154e0b1b7808e995e5f532e853","source":{"kind":"arxiv","id":"2312.08852","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08852","created_at":"2026-07-05T07:53:49Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08852v2","created_at":"2026-07-05T07:53:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08852","created_at":"2026-07-05T07:53:49Z"},{"alias_kind":"pith_short_12","alias_value":"VYERO7SUNC3U","created_at":"2026-07-05T07:53:49Z"},{"alias_kind":"pith_short_16","alias_value":"VYERO7SUNC3UQTKT","created_at":"2026-07-05T07:53:49Z"},{"alias_kind":"pith_short_8","alias_value":"VYERO7SU","created_at":"2026-07-05T07:53:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VYERO7SUNC3UQTKTD5RXNZ2ADB","target":"record","payload":{"canonical_record":{"source":{"id":"2312.08852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T17:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"85a3ad2762fd779874ecafd0f52af6b24f0a266d94bbe3aec81cb024d8c108af","abstract_canon_sha256":"790d3963e6b0a8512d49e589d7d95ea24e83e7a2f66b46eb235c13f1fdb50587"},"schema_version":"1.0"},"canonical_sha256":"ae09177e5468b7484d531f6376e7401872680d154e0b1b7808e995e5f532e853","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:49.692729Z","signature_b64":"xNs6djWW1e+QsuW17H7nZOSRmd6kbtt8wyLpg5enKX3+vuCVIGUltlamSSIGSWHUCwJkSpRYiInt2RwjGXEvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae09177e5468b7484d531f6376e7401872680d154e0b1b7808e995e5f532e853","last_reissued_at":"2026-07-05T07:53:49.692231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:49.692231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.08852","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":"2026-07-05T07:53:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"80B2kebc1TEqgQrKWeOqaVrZA1GncdN8lklVK1kkmYdmmSOcM/srmRBWzTPzMpfNoj+PlHk7T63eJ4o5/JmiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:11:33.202247Z"},"content_sha256":"4c3e3404a606cc11363b539a53b151ec34b99a5f345527528429358e23a8f336","schema_version":"1.0","event_id":"sha256:4c3e3404a606cc11363b539a53b151ec34b99a5f345527528429358e23a8f336"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VYERO7SUNC3UQTKTD5RXNZ2ADB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Liangcai Su, Ling-Hao Chen, Taohua Huang, Tongliang Liu, Xiaobo Xia, Xi Xiao, Yuanshuo Zhang, Zeyi Lin","submitted_at":"2023-12-13T17:59:07Z","abstract_excerpt":"Deep learning has achieved remarkable success in graph-related tasks, yet this accomplishment heavily relies on large-scale high-quality annotated datasets. However, acquiring such datasets can be cost-prohibitive, leading to the practical use of labels obtained from economically efficient sources such as web searches and user tags. Unfortunately, these labels often come with noise, compromising the generalization performance of deep networks. To tackle this challenge and enhance the robustness of deep learning models against label noise in graph-based tasks, we propose a method called ERASE ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08852","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/2312.08852/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":"2026-07-05T07:53:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3QG57nkdZ6X/l00J9k9bo1DD5oJegvpoQbg3UY9xJi41dwdLxdJ7dtytZ3Eb/YVs/1BsK2I4ER7Rjb/Vx6RGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:11:33.202750Z"},"content_sha256":"7f7e96f120a940a5e3411fa79cbdf5008b84a6b78869eb318813f0eedc970dff","schema_version":"1.0","event_id":"sha256:7f7e96f120a940a5e3411fa79cbdf5008b84a6b78869eb318813f0eedc970dff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VYERO7SUNC3UQTKTD5RXNZ2ADB/bundle.json","state_url":"https://pith.science/pith/VYERO7SUNC3UQTKTD5RXNZ2ADB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VYERO7SUNC3UQTKTD5RXNZ2ADB/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":"2026-08-04T12:11:33Z","links":{"resolver":"https://pith.science/pith/VYERO7SUNC3UQTKTD5RXNZ2ADB","bundle":"https://pith.science/pith/VYERO7SUNC3UQTKTD5RXNZ2ADB/bundle.json","state":"https://pith.science/pith/VYERO7SUNC3UQTKTD5RXNZ2ADB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VYERO7SUNC3UQTKTD5RXNZ2ADB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VYERO7SUNC3UQTKTD5RXNZ2ADB","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":"790d3963e6b0a8512d49e589d7d95ea24e83e7a2f66b46eb235c13f1fdb50587","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T17:59:07Z","title_canon_sha256":"85a3ad2762fd779874ecafd0f52af6b24f0a266d94bbe3aec81cb024d8c108af"},"schema_version":"1.0","source":{"id":"2312.08852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.08852","created_at":"2026-07-05T07:53:49Z"},{"alias_kind":"arxiv_version","alias_value":"2312.08852v2","created_at":"2026-07-05T07:53:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08852","created_at":"2026-07-05T07:53:49Z"},{"alias_kind":"pith_short_12","alias_value":"VYERO7SUNC3U","created_at":"2026-07-05T07:53:49Z"},{"alias_kind":"pith_short_16","alias_value":"VYERO7SUNC3UQTKT","created_at":"2026-07-05T07:53:49Z"},{"alias_kind":"pith_short_8","alias_value":"VYERO7SU","created_at":"2026-07-05T07:53:49Z"}],"graph_snapshots":[{"event_id":"sha256:7f7e96f120a940a5e3411fa79cbdf5008b84a6b78869eb318813f0eedc970dff","target":"graph","created_at":"2026-07-05T07:53:49Z","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/2312.08852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning has achieved remarkable success in graph-related tasks, yet this accomplishment heavily relies on large-scale high-quality annotated datasets. However, acquiring such datasets can be cost-prohibitive, leading to the practical use of labels obtained from economically efficient sources such as web searches and user tags. Unfortunately, these labels often come with noise, compromising the generalization performance of deep networks. To tackle this challenge and enhance the robustness of deep learning models against label noise in graph-based tasks, we propose a method called ERASE (","authors_text":"Liangcai Su, Ling-Hao Chen, Taohua Huang, Tongliang Liu, Xiaobo Xia, Xi Xiao, Yuanshuo Zhang, Zeyi Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T17:59:07Z","title":"ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08852","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":"sha256:4c3e3404a606cc11363b539a53b151ec34b99a5f345527528429358e23a8f336","target":"record","created_at":"2026-07-05T07:53:49Z","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":"790d3963e6b0a8512d49e589d7d95ea24e83e7a2f66b46eb235c13f1fdb50587","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-13T17:59:07Z","title_canon_sha256":"85a3ad2762fd779874ecafd0f52af6b24f0a266d94bbe3aec81cb024d8c108af"},"schema_version":"1.0","source":{"id":"2312.08852","kind":"arxiv","version":2}},"canonical_sha256":"ae09177e5468b7484d531f6376e7401872680d154e0b1b7808e995e5f532e853","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae09177e5468b7484d531f6376e7401872680d154e0b1b7808e995e5f532e853","first_computed_at":"2026-07-05T07:53:49.692231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:49.692231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xNs6djWW1e+QsuW17H7nZOSRmd6kbtt8wyLpg5enKX3+vuCVIGUltlamSSIGSWHUCwJkSpRYiInt2RwjGXEvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:49.692729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.08852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c3e3404a606cc11363b539a53b151ec34b99a5f345527528429358e23a8f336","sha256:7f7e96f120a940a5e3411fa79cbdf5008b84a6b78869eb318813f0eedc970dff"],"state_sha256":"f1ccffa4aeee30debd523167d37ca5d63cdc84bed2128c33fc7552030e91e2b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g5QAuxUbNQSP1s/MWskOhC2I8dPB7KihxNWemZOFMhIQSxXTcgGPQOA9T1Mx4jy2cn93o8FakW85giICUtIJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:11:33.207606Z","bundle_sha256":"eb005142b71e72bad10b6da418adb7fa1ebd11f922af6548947aebaf4323187b"}}