{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LFSIUL5OJT34URKPRGEIJRZXZS","short_pith_number":"pith:LFSIUL5O","schema_version":"1.0","canonical_sha256":"59648a2fae4cf7ca454f898884c737cc8f8944f7f920e3b6499ff66e0fe81d13","source":{"kind":"arxiv","id":"2202.13248","version":4},"attestation_state":"computed","paper":{"title":"Automated Data Augmentations for Graph Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kanji Uchino, Koji Maruhashi, Michael McThrow, Shuiwang Ji, Tao Komikado, Wing Yee Au, Youzhi Luo","submitted_at":"2022-02-26T23:00:34Z","abstract_excerpt":"Data augmentations are effective in improving the invariance of learning machines. We argue that the core challenge of data augmentations lies in designing data transformations that preserve labels. This is relatively straightforward for images, but much more challenging for graphs. In this work, we propose GraphAug, a novel automated data augmentation method aiming at computing label-invariant augmentations for graph classification. Instead of using uniform transformations as in existing studies, GraphAug uses an automated augmentation model to avoid compromising critical label-related inform"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.13248","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-26T23:00:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9f884cb1abbcc39d86b5a7e23f32e3c4679e0a6bc3572d68cf46b212ca89488e","abstract_canon_sha256":"bd926f13c629f4ca730e056ee72f4b8be6b3ab0ccc00b04db4b670d7e0c400bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:46:13.281823Z","signature_b64":"QUS2THol3Q7xwCgF63x0+7IVxZYT+ntT2gxW5ZPF/uHueIw1cH1ydSC10UjHlOyiBkY5DS4BPPZlRwMS5mJgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59648a2fae4cf7ca454f898884c737cc8f8944f7f920e3b6499ff66e0fe81d13","last_reissued_at":"2026-07-05T05:46:13.281306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:46:13.281306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Data Augmentations for Graph Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kanji Uchino, Koji Maruhashi, Michael McThrow, Shuiwang Ji, Tao Komikado, Wing Yee Au, Youzhi Luo","submitted_at":"2022-02-26T23:00:34Z","abstract_excerpt":"Data augmentations are effective in improving the invariance of learning machines. We argue that the core challenge of data augmentations lies in designing data transformations that preserve labels. This is relatively straightforward for images, but much more challenging for graphs. In this work, we propose GraphAug, a novel automated data augmentation method aiming at computing label-invariant augmentations for graph classification. Instead of using uniform transformations as in existing studies, GraphAug uses an automated augmentation model to avoid compromising critical label-related inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13248","kind":"arxiv","version":4},"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/2202.13248/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.13248","created_at":"2026-07-05T05:46:13.281386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13248v4","created_at":"2026-07-05T05:46:13.281386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13248","created_at":"2026-07-05T05:46:13.281386+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFSIUL5OJT34","created_at":"2026-07-05T05:46:13.281386+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFSIUL5OJT34URKP","created_at":"2026-07-05T05:46:13.281386+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFSIUL5O","created_at":"2026-07-05T05:46:13.281386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFSIUL5OJT34URKPRGEIJRZXZS","json":"https://pith.science/pith/LFSIUL5OJT34URKPRGEIJRZXZS.json","graph_json":"https://pith.science/api/pith-number/LFSIUL5OJT34URKPRGEIJRZXZS/graph.json","events_json":"https://pith.science/api/pith-number/LFSIUL5OJT34URKPRGEIJRZXZS/events.json","paper":"https://pith.science/paper/LFSIUL5O"},"agent_actions":{"view_html":"https://pith.science/pith/LFSIUL5OJT34URKPRGEIJRZXZS","download_json":"https://pith.science/pith/LFSIUL5OJT34URKPRGEIJRZXZS.json","view_paper":"https://pith.science/paper/LFSIUL5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13248&json=true","fetch_graph":"https://pith.science/api/pith-number/LFSIUL5OJT34URKPRGEIJRZXZS/graph.json","fetch_events":"https://pith.science/api/pith-number/LFSIUL5OJT34URKPRGEIJRZXZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFSIUL5OJT34URKPRGEIJRZXZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFSIUL5OJT34URKPRGEIJRZXZS/action/storage_attestation","attest_author":"https://pith.science/pith/LFSIUL5OJT34URKPRGEIJRZXZS/action/author_attestation","sign_citation":"https://pith.science/pith/LFSIUL5OJT34URKPRGEIJRZXZS/action/citation_signature","submit_replication":"https://pith.science/pith/LFSIUL5OJT34URKPRGEIJRZXZS/action/replication_record"}},"created_at":"2026-07-05T05:46:13.281386+00:00","updated_at":"2026-07-05T05:46:13.281386+00:00"}