{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FMYQHBQ6YYTNHMX4DCNAGL47EZ","short_pith_number":"pith:FMYQHBQ6","canonical_record":{"source":{"id":"2110.06290","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-12T19:24:42Z","cross_cats_sorted":[],"title_canon_sha256":"ed4806a55cf5d84686305c444a83209dbeaded44da9aac5fe6256aa27189506d","abstract_canon_sha256":"35f8c3fd0271f08d66ccf70c5c0a232fde4509366a8d5b0aee2577f9b2bf0611"},"schema_version":"1.0"},"canonical_sha256":"2b3103861ec626d3b2fc189a032f9f2656aacce9432d46e015283b245c587f76","source":{"kind":"arxiv","id":"2110.06290","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06290","created_at":"2026-07-05T03:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06290v1","created_at":"2026-07-05T03:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06290","created_at":"2026-07-05T03:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"FMYQHBQ6YYTN","created_at":"2026-07-05T03:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"FMYQHBQ6YYTNHMX4","created_at":"2026-07-05T03:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"FMYQHBQ6","created_at":"2026-07-05T03:22:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FMYQHBQ6YYTNHMX4DCNAGL47EZ","target":"record","payload":{"canonical_record":{"source":{"id":"2110.06290","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-12T19:24:42Z","cross_cats_sorted":[],"title_canon_sha256":"ed4806a55cf5d84686305c444a83209dbeaded44da9aac5fe6256aa27189506d","abstract_canon_sha256":"35f8c3fd0271f08d66ccf70c5c0a232fde4509366a8d5b0aee2577f9b2bf0611"},"schema_version":"1.0"},"canonical_sha256":"2b3103861ec626d3b2fc189a032f9f2656aacce9432d46e015283b245c587f76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:13.220881Z","signature_b64":"BJovO0n/PC+CcZq1YHYOfZN15cY0PCSc87JknVAsa/fX7Tr/eH+L0qF7IGzLZrT8oJTYE4+OvK+KB7LEfRsHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b3103861ec626d3b2fc189a032f9f2656aacce9432d46e015283b245c587f76","last_reissued_at":"2026-07-05T03:22:13.220468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:13.220468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.06290","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":"2026-07-05T03:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DEa3mtYM/X3P95X/NUrUR2h5fnf6EowuD2AMcL/dF+pNJaLolb4JLpL47/4idb1aLsVZpIv/7kPA+xgyv+AuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T03:30:22.306155Z"},"content_sha256":"e4921033fdc3af713ed0ea2d541dbb153c519d2b9c6d7c0bae26d9db3becfcac","schema_version":"1.0","event_id":"sha256:e4921033fdc3af713ed0ea2d541dbb153c519d2b9c6d7c0bae26d9db3becfcac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FMYQHBQ6YYTNHMX4DCNAGL47EZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cole Hawkins, George Karypis, Soji Adeshina, Vassilis N. Ioannidis","submitted_at":"2021-10-12T19:24:42Z","abstract_excerpt":"Consistency training is a popular method to improve deep learning models in computer vision and natural language processing. Graph neural networks (GNNs) have achieved remarkable performance in a variety of network science learning tasks, but to date no work has studied the effect of consistency training on large-scale graph problems. GNNs scale to large graphs by minibatch training and subsample node neighbors to deal with high degree nodes. We utilize the randomness inherent in the subsampling of neighbors and introduce a novel consistency training method to improve accuracy. For a target no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06290","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/2110.06290/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":"2026-07-05T03:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vh8xXcXbOR9QOwf8k+RmXUx19sSIrbBgC+JlncBAMY29RuAK5zzkiujQO7rU5IWwWZKkxS5oyP3RHgzTu/paAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T03:30:22.306539Z"},"content_sha256":"cf76e825dd9d4f05b176504d187fdc5f8228191cdbb84314bb5155ba17485c3a","schema_version":"1.0","event_id":"sha256:cf76e825dd9d4f05b176504d187fdc5f8228191cdbb84314bb5155ba17485c3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMYQHBQ6YYTNHMX4DCNAGL47EZ/bundle.json","state_url":"https://pith.science/pith/FMYQHBQ6YYTNHMX4DCNAGL47EZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMYQHBQ6YYTNHMX4DCNAGL47EZ/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":"2026-07-25T03:30:22Z","links":{"resolver":"https://pith.science/pith/FMYQHBQ6YYTNHMX4DCNAGL47EZ","bundle":"https://pith.science/pith/FMYQHBQ6YYTNHMX4DCNAGL47EZ/bundle.json","state":"https://pith.science/pith/FMYQHBQ6YYTNHMX4DCNAGL47EZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMYQHBQ6YYTNHMX4DCNAGL47EZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FMYQHBQ6YYTNHMX4DCNAGL47EZ","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":"35f8c3fd0271f08d66ccf70c5c0a232fde4509366a8d5b0aee2577f9b2bf0611","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-12T19:24:42Z","title_canon_sha256":"ed4806a55cf5d84686305c444a83209dbeaded44da9aac5fe6256aa27189506d"},"schema_version":"1.0","source":{"id":"2110.06290","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06290","created_at":"2026-07-05T03:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06290v1","created_at":"2026-07-05T03:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06290","created_at":"2026-07-05T03:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"FMYQHBQ6YYTN","created_at":"2026-07-05T03:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"FMYQHBQ6YYTNHMX4","created_at":"2026-07-05T03:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"FMYQHBQ6","created_at":"2026-07-05T03:22:13Z"}],"graph_snapshots":[{"event_id":"sha256:cf76e825dd9d4f05b176504d187fdc5f8228191cdbb84314bb5155ba17485c3a","target":"graph","created_at":"2026-07-05T03:22:13Z","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/2110.06290/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consistency training is a popular method to improve deep learning models in computer vision and natural language processing. Graph neural networks (GNNs) have achieved remarkable performance in a variety of network science learning tasks, but to date no work has studied the effect of consistency training on large-scale graph problems. GNNs scale to large graphs by minibatch training and subsample node neighbors to deal with high degree nodes. We utilize the randomness inherent in the subsampling of neighbors and introduce a novel consistency training method to improve accuracy. For a target no","authors_text":"Cole Hawkins, George Karypis, Soji Adeshina, Vassilis N. Ioannidis","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-12T19:24:42Z","title":"Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06290","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:e4921033fdc3af713ed0ea2d541dbb153c519d2b9c6d7c0bae26d9db3becfcac","target":"record","created_at":"2026-07-05T03:22:13Z","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":"35f8c3fd0271f08d66ccf70c5c0a232fde4509366a8d5b0aee2577f9b2bf0611","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-12T19:24:42Z","title_canon_sha256":"ed4806a55cf5d84686305c444a83209dbeaded44da9aac5fe6256aa27189506d"},"schema_version":"1.0","source":{"id":"2110.06290","kind":"arxiv","version":1}},"canonical_sha256":"2b3103861ec626d3b2fc189a032f9f2656aacce9432d46e015283b245c587f76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b3103861ec626d3b2fc189a032f9f2656aacce9432d46e015283b245c587f76","first_computed_at":"2026-07-05T03:22:13.220468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:13.220468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BJovO0n/PC+CcZq1YHYOfZN15cY0PCSc87JknVAsa/fX7Tr/eH+L0qF7IGzLZrT8oJTYE4+OvK+KB7LEfRsHAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:13.220881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06290","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4921033fdc3af713ed0ea2d541dbb153c519d2b9c6d7c0bae26d9db3becfcac","sha256:cf76e825dd9d4f05b176504d187fdc5f8228191cdbb84314bb5155ba17485c3a"],"state_sha256":"6352f8666b94d2e2d7df426d6435283244449140e20420d3ce3cd8dd7c6ec81b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lqe6Oy7RHYmTjCndnVU3xNLpJGdO683LMu4BnpaOwxV9IaZphRF/vZuxedaIJc6oKRdzSpi8kPt0DqwgdnC+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T03:30:22.308650Z","bundle_sha256":"8324ce2f47c155b0fd3e5f7b3815d22a4746b58f748d289afadadb9de7dc5613"}}