{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OYXYVXFILLDWP7ZZJL7NUZ2S2L","short_pith_number":"pith:OYXYVXFI","canonical_record":{"source":{"id":"2404.17875","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-27T12:19:08Z","cross_cats_sorted":[],"title_canon_sha256":"73d93c77511fd05b7b374b1b43412d95094b6f43656e20f57f90d10a9cf18b37","abstract_canon_sha256":"8553caf589002c11c8f6d02307df0f67a24ba2f8f0d393ef5e975d5b8051ac72"},"schema_version":"1.0"},"canonical_sha256":"762f8adca85ac767ff394afeda6752d2eb2eb787b3d0ffe309f7ffe8238cf910","source":{"kind":"arxiv","id":"2404.17875","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17875","created_at":"2026-07-05T08:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17875v2","created_at":"2026-07-05T08:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17875","created_at":"2026-07-05T08:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"OYXYVXFILLDW","created_at":"2026-07-05T08:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"OYXYVXFILLDWP7ZZ","created_at":"2026-07-05T08:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"OYXYVXFI","created_at":"2026-07-05T08:16:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OYXYVXFILLDWP7ZZJL7NUZ2S2L","target":"record","payload":{"canonical_record":{"source":{"id":"2404.17875","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-27T12:19:08Z","cross_cats_sorted":[],"title_canon_sha256":"73d93c77511fd05b7b374b1b43412d95094b6f43656e20f57f90d10a9cf18b37","abstract_canon_sha256":"8553caf589002c11c8f6d02307df0f67a24ba2f8f0d393ef5e975d5b8051ac72"},"schema_version":"1.0"},"canonical_sha256":"762f8adca85ac767ff394afeda6752d2eb2eb787b3d0ffe309f7ffe8238cf910","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:49.137397Z","signature_b64":"N9q8FaU9zq/f0cC/bcMUC4VYdUa+60KpPh4SdQgiurY3HnSO64kjapVW5DxwgYqRK29cc/iqNiArI9dovLKnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"762f8adca85ac767ff394afeda6752d2eb2eb787b3d0ffe309f7ffe8238cf910","last_reissued_at":"2026-07-05T08:16:49.136980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:49.136980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.17875","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":"2026-07-05T08:16:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YHsQZ5To6BE5+y5Q/t0K2i0UCZtmQ2gQi5FE2Hq+9DQSq+Eht2zOrUlUH2Z2O08cwPmp69rq57UXJOuJLHN8AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T09:06:28.036191Z"},"content_sha256":"5da370012c3cb12b55a9179cdb44ffbfd82ea42405cc92719a48971c391a26fe","schema_version":"1.0","event_id":"sha256:5da370012c3cb12b55a9179cdb44ffbfd82ea42405cc92719a48971c391a26fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OYXYVXFILLDWP7ZZJL7NUZ2S2L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noisy Node Classification by Bi-level Optimization based Multi-teacher Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ci Nie, Guoqiu Wen, Ping Hu, Xiaofeng Zhu, Yujing Liu, Zhengyu Lu, Zongqian Wu","submitted_at":"2024-04-27T12:19:08Z","abstract_excerpt":"Previous graph neural networks (GNNs) usually assume that the graph data is with clean labels for representation learning, but it is not true in real applications. In this paper, we propose a new multi-teacher distillation method based on bi-level optimization (namely BO-NNC), to conduct noisy node classification on the graph data. Specifically, we first employ multiple self-supervised learning methods to train diverse teacher models, and then aggregate their predictions through a teacher weight matrix. Furthermore, we design a new bi-level optimization strategy to dynamically adjust the teach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17875","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/2404.17875/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":"2026-07-05T08:16:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3YuJb/1t0Uhuzsv72Fn3Cd3dUXVz0FlGtB7O3AhmbsKN/BYhWddSelTkKK5ItWCNWi9YWDQZtaqv8LzOXh6sAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T09:06:28.036873Z"},"content_sha256":"7c4283c04f66149ffc15eeb07a5312c4eda2a3cec3eff4abfd8c3263e6df959b","schema_version":"1.0","event_id":"sha256:7c4283c04f66149ffc15eeb07a5312c4eda2a3cec3eff4abfd8c3263e6df959b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OYXYVXFILLDWP7ZZJL7NUZ2S2L/bundle.json","state_url":"https://pith.science/pith/OYXYVXFILLDWP7ZZJL7NUZ2S2L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OYXYVXFILLDWP7ZZJL7NUZ2S2L/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":"2026-08-16T09:06:28Z","links":{"resolver":"https://pith.science/pith/OYXYVXFILLDWP7ZZJL7NUZ2S2L","bundle":"https://pith.science/pith/OYXYVXFILLDWP7ZZJL7NUZ2S2L/bundle.json","state":"https://pith.science/pith/OYXYVXFILLDWP7ZZJL7NUZ2S2L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OYXYVXFILLDWP7ZZJL7NUZ2S2L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OYXYVXFILLDWP7ZZJL7NUZ2S2L","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":"8553caf589002c11c8f6d02307df0f67a24ba2f8f0d393ef5e975d5b8051ac72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-27T12:19:08Z","title_canon_sha256":"73d93c77511fd05b7b374b1b43412d95094b6f43656e20f57f90d10a9cf18b37"},"schema_version":"1.0","source":{"id":"2404.17875","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17875","created_at":"2026-07-05T08:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17875v2","created_at":"2026-07-05T08:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17875","created_at":"2026-07-05T08:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"OYXYVXFILLDW","created_at":"2026-07-05T08:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"OYXYVXFILLDWP7ZZ","created_at":"2026-07-05T08:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"OYXYVXFI","created_at":"2026-07-05T08:16:49Z"}],"graph_snapshots":[{"event_id":"sha256:7c4283c04f66149ffc15eeb07a5312c4eda2a3cec3eff4abfd8c3263e6df959b","target":"graph","created_at":"2026-07-05T08:16:49Z","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/2404.17875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous graph neural networks (GNNs) usually assume that the graph data is with clean labels for representation learning, but it is not true in real applications. In this paper, we propose a new multi-teacher distillation method based on bi-level optimization (namely BO-NNC), to conduct noisy node classification on the graph data. Specifically, we first employ multiple self-supervised learning methods to train diverse teacher models, and then aggregate their predictions through a teacher weight matrix. Furthermore, we design a new bi-level optimization strategy to dynamically adjust the teach","authors_text":"Ci Nie, Guoqiu Wen, Ping Hu, Xiaofeng Zhu, Yujing Liu, Zhengyu Lu, Zongqian Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-27T12:19:08Z","title":"Noisy Node Classification by Bi-level Optimization based Multi-teacher Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17875","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":"sha256:5da370012c3cb12b55a9179cdb44ffbfd82ea42405cc92719a48971c391a26fe","target":"record","created_at":"2026-07-05T08:16:49Z","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":"8553caf589002c11c8f6d02307df0f67a24ba2f8f0d393ef5e975d5b8051ac72","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-27T12:19:08Z","title_canon_sha256":"73d93c77511fd05b7b374b1b43412d95094b6f43656e20f57f90d10a9cf18b37"},"schema_version":"1.0","source":{"id":"2404.17875","kind":"arxiv","version":2}},"canonical_sha256":"762f8adca85ac767ff394afeda6752d2eb2eb787b3d0ffe309f7ffe8238cf910","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"762f8adca85ac767ff394afeda6752d2eb2eb787b3d0ffe309f7ffe8238cf910","first_computed_at":"2026-07-05T08:16:49.136980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:49.136980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N9q8FaU9zq/f0cC/bcMUC4VYdUa+60KpPh4SdQgiurY3HnSO64kjapVW5DxwgYqRK29cc/iqNiArI9dovLKnCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:49.137397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.17875","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5da370012c3cb12b55a9179cdb44ffbfd82ea42405cc92719a48971c391a26fe","sha256:7c4283c04f66149ffc15eeb07a5312c4eda2a3cec3eff4abfd8c3263e6df959b"],"state_sha256":"e1e7a27af70d0b5762732be130daa0b78230d2bc30a0122c80a0238948c8eea8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dac6L3G3GWkJQ3kw/hvDZudRN66L0R+n5xke6BGPwKcwBWrk3OZ+Ah+2c+T8hT5M2VLztxJaZoA3Zww4BqupCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T09:06:28.047646Z","bundle_sha256":"f9894c618992307d92fd00813d7bee8af1aa43af75147352d5b70c52d804ed07"}}