{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZVA6AKTNO2YLJ6K5PJMKIOLX6J","short_pith_number":"pith:ZVA6AKTN","schema_version":"1.0","canonical_sha256":"cd41e02a6d76b0b4f95d7a58a43977f25510ab65f9cdf386e0dfdcee30bc4dd8","source":{"kind":"arxiv","id":"2210.08813","version":1},"attestation_state":"computed","paper":{"title":"Test-Time Training for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaozhuo Li, Jianan Zhao, Jiliang Tang, Rui Li, Wei Jin, Xing Xie, Yiqi Wang","submitted_at":"2022-10-17T07:58:07Z","abstract_excerpt":"Graph Neural Networks (GNNs) have made tremendous progress in the graph classification task. However, a performance gap between the training set and the test set has often been noticed. To bridge such gap, in this work we introduce the first test-time training framework for GNNs to enhance the model generalization capacity for the graph classification task. In particular, we design a novel test-time training strategy with self-supervised learning to adjust the GNN model for each test graph sample. Experiments on the benchmark datasets have demonstrated the effectiveness of the proposed framewo"},"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":"2210.08813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-17T07:58:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"81f4612536048fa63fd7560e700e7a004ff37af543eab2287b3b9eacf1155a05","abstract_canon_sha256":"f42921b660164987437df3ec696bafe86bb5d5b7e5f6a8830638a81237543936"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:15.444406Z","signature_b64":"/JIHq+qMx9DDQYWmG+VmnzfMfhh3SsURrKTBfF5K2euiK37cxemjBmgytAbYXLGhDAZ3cutBb3+UHcocQtppAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd41e02a6d76b0b4f95d7a58a43977f25510ab65f9cdf386e0dfdcee30bc4dd8","last_reissued_at":"2026-07-05T05:07:15.444012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:15.444012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-Time Training for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaozhuo Li, Jianan Zhao, Jiliang Tang, Rui Li, Wei Jin, Xing Xie, Yiqi Wang","submitted_at":"2022-10-17T07:58:07Z","abstract_excerpt":"Graph Neural Networks (GNNs) have made tremendous progress in the graph classification task. However, a performance gap between the training set and the test set has often been noticed. To bridge such gap, in this work we introduce the first test-time training framework for GNNs to enhance the model generalization capacity for the graph classification task. In particular, we design a novel test-time training strategy with self-supervised learning to adjust the GNN model for each test graph sample. Experiments on the benchmark datasets have demonstrated the effectiveness of the proposed framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08813","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/2210.08813/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":"2210.08813","created_at":"2026-07-05T05:07:15.444064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08813v1","created_at":"2026-07-05T05:07:15.444064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08813","created_at":"2026-07-05T05:07:15.444064+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVA6AKTNO2YL","created_at":"2026-07-05T05:07:15.444064+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVA6AKTNO2YLJ6K5","created_at":"2026-07-05T05:07:15.444064+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVA6AKTN","created_at":"2026-07-05T05:07:15.444064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22914","citing_title":"PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZVA6AKTNO2YLJ6K5PJMKIOLX6J","json":"https://pith.science/pith/ZVA6AKTNO2YLJ6K5PJMKIOLX6J.json","graph_json":"https://pith.science/api/pith-number/ZVA6AKTNO2YLJ6K5PJMKIOLX6J/graph.json","events_json":"https://pith.science/api/pith-number/ZVA6AKTNO2YLJ6K5PJMKIOLX6J/events.json","paper":"https://pith.science/paper/ZVA6AKTN"},"agent_actions":{"view_html":"https://pith.science/pith/ZVA6AKTNO2YLJ6K5PJMKIOLX6J","download_json":"https://pith.science/pith/ZVA6AKTNO2YLJ6K5PJMKIOLX6J.json","view_paper":"https://pith.science/paper/ZVA6AKTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08813&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVA6AKTNO2YLJ6K5PJMKIOLX6J/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVA6AKTNO2YLJ6K5PJMKIOLX6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVA6AKTNO2YLJ6K5PJMKIOLX6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVA6AKTNO2YLJ6K5PJMKIOLX6J/action/storage_attestation","attest_author":"https://pith.science/pith/ZVA6AKTNO2YLJ6K5PJMKIOLX6J/action/author_attestation","sign_citation":"https://pith.science/pith/ZVA6AKTNO2YLJ6K5PJMKIOLX6J/action/citation_signature","submit_replication":"https://pith.science/pith/ZVA6AKTNO2YLJ6K5PJMKIOLX6J/action/replication_record"}},"created_at":"2026-07-05T05:07:15.444064+00:00","updated_at":"2026-07-05T05:07:15.444064+00:00"}