{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XGHVW5XLKLS3Y2N4F5YKVYQOQD","short_pith_number":"pith:XGHVW5XL","schema_version":"1.0","canonical_sha256":"b98f5b76eb52e5bc69bc2f70aae20e80f8a978d374d662496f7e000270104c3b","source":{"kind":"arxiv","id":"2208.09126","version":1},"attestation_state":"computed","paper":{"title":"GraphTTA: Test Time Adaptation on Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guanzi Chen, Jiying Zhang, Xi Xiao, Yang Li","submitted_at":"2022-08-19T02:24:16Z","abstract_excerpt":"Recently, test time adaptation (TTA) has attracted increasing attention due to its power of handling the distribution shift issue in the real world. Unlike what has been developed for convolutional neural networks (CNNs) for image data, TTA is less explored for Graph Neural Networks (GNNs). There is still a lack of efficient algorithms tailored for graphs with irregular structures. In this paper, we present a novel test time adaptation strategy named Graph Adversarial Pseudo Group Contrast (GAPGC), for graph neural networks TTA, to better adapt to the Out Of Distribution (OOD) test data. Speci"},"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":"2208.09126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-19T02:24:16Z","cross_cats_sorted":[],"title_canon_sha256":"3f589f1a65b3e73a7b68e3f84d4313bed3d705a232b195366576763a582a6958","abstract_canon_sha256":"0f14c30cd8e5f6598d108e599183a8761df0881d8aab71bb82067bc4d3e90d8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:56.258374Z","signature_b64":"w68qFQIHTvcWkV71MIG05Kcz11Qb/zsLBBxMTuffdLtuvtD+wiMrAxrJNGG/K7h4ivMqtqhe3LmjOWtcAO1UAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b98f5b76eb52e5bc69bc2f70aae20e80f8a978d374d662496f7e000270104c3b","last_reissued_at":"2026-07-05T04:49:56.257928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:56.257928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphTTA: Test Time Adaptation on Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guanzi Chen, Jiying Zhang, Xi Xiao, Yang Li","submitted_at":"2022-08-19T02:24:16Z","abstract_excerpt":"Recently, test time adaptation (TTA) has attracted increasing attention due to its power of handling the distribution shift issue in the real world. Unlike what has been developed for convolutional neural networks (CNNs) for image data, TTA is less explored for Graph Neural Networks (GNNs). There is still a lack of efficient algorithms tailored for graphs with irregular structures. In this paper, we present a novel test time adaptation strategy named Graph Adversarial Pseudo Group Contrast (GAPGC), for graph neural networks TTA, to better adapt to the Out Of Distribution (OOD) test data. Speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09126","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/2208.09126/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":"2208.09126","created_at":"2026-07-05T04:49:56.257983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.09126v1","created_at":"2026-07-05T04:49:56.257983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09126","created_at":"2026-07-05T04:49:56.257983+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGHVW5XLKLS3","created_at":"2026-07-05T04:49:56.257983+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGHVW5XLKLS3Y2N4","created_at":"2026-07-05T04:49:56.257983+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGHVW5XL","created_at":"2026-07-05T04:49:56.257983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22914","citing_title":"PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29526","citing_title":"Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGHVW5XLKLS3Y2N4F5YKVYQOQD","json":"https://pith.science/pith/XGHVW5XLKLS3Y2N4F5YKVYQOQD.json","graph_json":"https://pith.science/api/pith-number/XGHVW5XLKLS3Y2N4F5YKVYQOQD/graph.json","events_json":"https://pith.science/api/pith-number/XGHVW5XLKLS3Y2N4F5YKVYQOQD/events.json","paper":"https://pith.science/paper/XGHVW5XL"},"agent_actions":{"view_html":"https://pith.science/pith/XGHVW5XLKLS3Y2N4F5YKVYQOQD","download_json":"https://pith.science/pith/XGHVW5XLKLS3Y2N4F5YKVYQOQD.json","view_paper":"https://pith.science/paper/XGHVW5XL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.09126&json=true","fetch_graph":"https://pith.science/api/pith-number/XGHVW5XLKLS3Y2N4F5YKVYQOQD/graph.json","fetch_events":"https://pith.science/api/pith-number/XGHVW5XLKLS3Y2N4F5YKVYQOQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGHVW5XLKLS3Y2N4F5YKVYQOQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGHVW5XLKLS3Y2N4F5YKVYQOQD/action/storage_attestation","attest_author":"https://pith.science/pith/XGHVW5XLKLS3Y2N4F5YKVYQOQD/action/author_attestation","sign_citation":"https://pith.science/pith/XGHVW5XLKLS3Y2N4F5YKVYQOQD/action/citation_signature","submit_replication":"https://pith.science/pith/XGHVW5XLKLS3Y2N4F5YKVYQOQD/action/replication_record"}},"created_at":"2026-07-05T04:49:56.257983+00:00","updated_at":"2026-07-05T04:49:56.257983+00:00"}