{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SK7LAKUNSPTH2YKBZQQNPE3RNI","short_pith_number":"pith:SK7LAKUN","canonical_record":{"source":{"id":"2010.09891","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-19T21:51:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7b39a3554c512b2e30c7e9911babf4f00a14e2f75bc7b74f6f9cf9e065e6fbfb","abstract_canon_sha256":"4a9d4ac85f8fc4fd9ad777c6f471823d6263ae31ffcd4d17a183215ab4a2fb9f"},"schema_version":"1.0"},"canonical_sha256":"92beb02a8d93e67d6141cc20d793716a1cbcbe477a056a7d716159701d1b2404","source":{"kind":"arxiv","id":"2010.09891","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.09891","created_at":"2026-07-05T04:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2010.09891v3","created_at":"2026-07-05T04:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09891","created_at":"2026-07-05T04:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"SK7LAKUNSPTH","created_at":"2026-07-05T04:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"SK7LAKUNSPTH2YKB","created_at":"2026-07-05T04:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"SK7LAKUN","created_at":"2026-07-05T04:09:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SK7LAKUNSPTH2YKBZQQNPE3RNI","target":"record","payload":{"canonical_record":{"source":{"id":"2010.09891","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-19T21:51:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7b39a3554c512b2e30c7e9911babf4f00a14e2f75bc7b74f6f9cf9e065e6fbfb","abstract_canon_sha256":"4a9d4ac85f8fc4fd9ad777c6f471823d6263ae31ffcd4d17a183215ab4a2fb9f"},"schema_version":"1.0"},"canonical_sha256":"92beb02a8d93e67d6141cc20d793716a1cbcbe477a056a7d716159701d1b2404","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:12.901815Z","signature_b64":"dVMLQUvU7W+EK/wB03KHV7pgmrPvAkuV8XK1+aL7+9xOS2J6DhI3q5MqjOpFChMlVaYvVVUiqnmHyNrG3foMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92beb02a8d93e67d6141cc20d793716a1cbcbe477a056a7d716159701d1b2404","last_reissued_at":"2026-07-05T04:09:12.901403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:12.901403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.09891","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/iGOu+vyJ7WzqeTizu2kHRgn0F+eYLYCR5mDhR/6koyuwvTySOjxLOG3hfdmvrZysmeVRauVg9RZYQ0mL3eeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:06:47.037650Z"},"content_sha256":"91e5e79d05f40e85851211d5580d4c3df721ef11a42f532adf3dfae6e2a81d0d","schema_version":"1.0","event_id":"sha256:91e5e79d05f40e85851211d5580d4c3df721ef11a42f532adf3dfae6e2a81d0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SK7LAKUNSPTH2YKBZQQNPE3RNI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Optimization as Data Augmentation for Large-scale Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernard Ghanem, Chen Zhu, Gavin Taylor, Guohao Li, Kezhi Kong, Mucong Ding, Tom Goldstein, Zuxuan Wu","submitted_at":"2020-10-19T21:51:47Z","abstract_excerpt":"Data augmentation helps neural networks generalize better by enlarging the training set, but it remains an open question how to effectively augment graph data to enhance the performance of GNNs (Graph Neural Networks). While most existing graph regularizers focus on manipulating graph topological structures by adding/removing edges, we offer a method to augment node features for better performance. We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. By making the model inv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09891","kind":"arxiv","version":3},"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/2010.09891/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":"2026-07-05T04:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0553pa1E2vUQGc6650oIpbdGovzt4PWjIgJgHOyR6iRymCVBp1z9gu+n3r1b6UDB8p5hKbCAj3vT54rf8/crBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:06:47.038187Z"},"content_sha256":"e34e9cc7d28bd605cd259b9b728eaf6e14db6a850602943bedf415bcb870f8e8","schema_version":"1.0","event_id":"sha256:e34e9cc7d28bd605cd259b9b728eaf6e14db6a850602943bedf415bcb870f8e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SK7LAKUNSPTH2YKBZQQNPE3RNI/bundle.json","state_url":"https://pith.science/pith/SK7LAKUNSPTH2YKBZQQNPE3RNI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SK7LAKUNSPTH2YKBZQQNPE3RNI/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":"2026-08-04T21:06:47Z","links":{"resolver":"https://pith.science/pith/SK7LAKUNSPTH2YKBZQQNPE3RNI","bundle":"https://pith.science/pith/SK7LAKUNSPTH2YKBZQQNPE3RNI/bundle.json","state":"https://pith.science/pith/SK7LAKUNSPTH2YKBZQQNPE3RNI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SK7LAKUNSPTH2YKBZQQNPE3RNI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SK7LAKUNSPTH2YKBZQQNPE3RNI","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":"4a9d4ac85f8fc4fd9ad777c6f471823d6263ae31ffcd4d17a183215ab4a2fb9f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-19T21:51:47Z","title_canon_sha256":"7b39a3554c512b2e30c7e9911babf4f00a14e2f75bc7b74f6f9cf9e065e6fbfb"},"schema_version":"1.0","source":{"id":"2010.09891","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.09891","created_at":"2026-07-05T04:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2010.09891v3","created_at":"2026-07-05T04:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09891","created_at":"2026-07-05T04:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"SK7LAKUNSPTH","created_at":"2026-07-05T04:09:12Z"},{"alias_kind":"pith_short_16","alias_value":"SK7LAKUNSPTH2YKB","created_at":"2026-07-05T04:09:12Z"},{"alias_kind":"pith_short_8","alias_value":"SK7LAKUN","created_at":"2026-07-05T04:09:12Z"}],"graph_snapshots":[{"event_id":"sha256:e34e9cc7d28bd605cd259b9b728eaf6e14db6a850602943bedf415bcb870f8e8","target":"graph","created_at":"2026-07-05T04:09:12Z","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/2010.09891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation helps neural networks generalize better by enlarging the training set, but it remains an open question how to effectively augment graph data to enhance the performance of GNNs (Graph Neural Networks). While most existing graph regularizers focus on manipulating graph topological structures by adding/removing edges, we offer a method to augment node features for better performance. We propose FLAG (Free Large-scale Adversarial Augmentation on Graphs), which iteratively augments node features with gradient-based adversarial perturbations during training. By making the model inv","authors_text":"Bernard Ghanem, Chen Zhu, Gavin Taylor, Guohao Li, Kezhi Kong, Mucong Ding, Tom Goldstein, Zuxuan Wu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-19T21:51:47Z","title":"Robust Optimization as Data Augmentation for Large-scale Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09891","kind":"arxiv","version":3},"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":"sha256:91e5e79d05f40e85851211d5580d4c3df721ef11a42f532adf3dfae6e2a81d0d","target":"record","created_at":"2026-07-05T04:09:12Z","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":"4a9d4ac85f8fc4fd9ad777c6f471823d6263ae31ffcd4d17a183215ab4a2fb9f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-19T21:51:47Z","title_canon_sha256":"7b39a3554c512b2e30c7e9911babf4f00a14e2f75bc7b74f6f9cf9e065e6fbfb"},"schema_version":"1.0","source":{"id":"2010.09891","kind":"arxiv","version":3}},"canonical_sha256":"92beb02a8d93e67d6141cc20d793716a1cbcbe477a056a7d716159701d1b2404","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92beb02a8d93e67d6141cc20d793716a1cbcbe477a056a7d716159701d1b2404","first_computed_at":"2026-07-05T04:09:12.901403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:12.901403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dVMLQUvU7W+EK/wB03KHV7pgmrPvAkuV8XK1+aL7+9xOS2J6DhI3q5MqjOpFChMlVaYvVVUiqnmHyNrG3foMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:12.901815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.09891","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91e5e79d05f40e85851211d5580d4c3df721ef11a42f532adf3dfae6e2a81d0d","sha256:e34e9cc7d28bd605cd259b9b728eaf6e14db6a850602943bedf415bcb870f8e8"],"state_sha256":"7f3bd9e73c04d941e6534f572fa7b6f34c0abe36adae50190ee15f1d585c14e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uE28cJWNymHDIsYTbVI+/Yh85JQmhWZcpcahNVALoEv9jP9hxyY/nLJOmz+2iuumn5mdCU1mj11yHQoUFOtJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:06:47.044305Z","bundle_sha256":"a854220b0b302c93204b377e24beb163f57874e8a179b8bd488e21b8088834ca"}}