{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SB5PHOEGVZ2GI7RVLFAVDJRPTT","short_pith_number":"pith:SB5PHOEG","schema_version":"1.0","canonical_sha256":"907af3b886ae74647e35594151a62f9cca4f3c0ab75583f0b565ec032f82103f","source":{"kind":"arxiv","id":"2410.06976","version":2},"attestation_state":"computed","paper":{"title":"Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hanghang Tong, Jingrui He, Wenxuan Bao, Zhichen Zeng, Zhining Liu","submitted_at":"2024-10-09T15:15:40Z","abstract_excerpt":"Powerful as they are, graph neural networks (GNNs) are known to be vulnerable to distribution shifts. Recently, test-time adaptation (TTA) has attracted attention due to its ability to adapt a pre-trained model to a target domain, without re-accessing the source domain. However, existing TTA algorithms are primarily designed for attribute shifts in vision tasks, where samples are independent. These methods perform poorly on graph data that experience structure shifts, where node connectivity differs between source and target graphs. We attribute this performance gap to the distinct impact of n"},"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":"2410.06976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T15:15:40Z","cross_cats_sorted":[],"title_canon_sha256":"54b9873deb723f874199354173aaa6ce321800f8e322bf9796504b0b827af181","abstract_canon_sha256":"1aee70c6549238d502165beea2dbd821656644867eebdab0548a106f7e25da0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:04.207259Z","signature_b64":"euBgh8LUI+iMqAHQ4aqd1mOOnbX9dnF2AyK55c4FVf1Hl/bfQES1sbgClhBk2Tjn3oW/G4aaM4C6w3Jygin1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"907af3b886ae74647e35594151a62f9cca4f3c0ab75583f0b565ec032f82103f","last_reissued_at":"2026-07-05T10:13:04.206771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:04.206771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matcha: Mitigating Graph Structure Shifts with Test-Time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hanghang Tong, Jingrui He, Wenxuan Bao, Zhichen Zeng, Zhining Liu","submitted_at":"2024-10-09T15:15:40Z","abstract_excerpt":"Powerful as they are, graph neural networks (GNNs) are known to be vulnerable to distribution shifts. Recently, test-time adaptation (TTA) has attracted attention due to its ability to adapt a pre-trained model to a target domain, without re-accessing the source domain. However, existing TTA algorithms are primarily designed for attribute shifts in vision tasks, where samples are independent. These methods perform poorly on graph data that experience structure shifts, where node connectivity differs between source and target graphs. We attribute this performance gap to the distinct impact of n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06976","kind":"arxiv","version":2},"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/2410.06976/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":"2410.06976","created_at":"2026-07-05T10:13:04.206822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06976v2","created_at":"2026-07-05T10:13:04.206822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06976","created_at":"2026-07-05T10:13:04.206822+00:00"},{"alias_kind":"pith_short_12","alias_value":"SB5PHOEGVZ2G","created_at":"2026-07-05T10:13:04.206822+00:00"},{"alias_kind":"pith_short_16","alias_value":"SB5PHOEGVZ2GI7RV","created_at":"2026-07-05T10:13:04.206822+00:00"},{"alias_kind":"pith_short_8","alias_value":"SB5PHOEG","created_at":"2026-07-05T10:13:04.206822+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09852","citing_title":"InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SB5PHOEGVZ2GI7RVLFAVDJRPTT","json":"https://pith.science/pith/SB5PHOEGVZ2GI7RVLFAVDJRPTT.json","graph_json":"https://pith.science/api/pith-number/SB5PHOEGVZ2GI7RVLFAVDJRPTT/graph.json","events_json":"https://pith.science/api/pith-number/SB5PHOEGVZ2GI7RVLFAVDJRPTT/events.json","paper":"https://pith.science/paper/SB5PHOEG"},"agent_actions":{"view_html":"https://pith.science/pith/SB5PHOEGVZ2GI7RVLFAVDJRPTT","download_json":"https://pith.science/pith/SB5PHOEGVZ2GI7RVLFAVDJRPTT.json","view_paper":"https://pith.science/paper/SB5PHOEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06976&json=true","fetch_graph":"https://pith.science/api/pith-number/SB5PHOEGVZ2GI7RVLFAVDJRPTT/graph.json","fetch_events":"https://pith.science/api/pith-number/SB5PHOEGVZ2GI7RVLFAVDJRPTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SB5PHOEGVZ2GI7RVLFAVDJRPTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SB5PHOEGVZ2GI7RVLFAVDJRPTT/action/storage_attestation","attest_author":"https://pith.science/pith/SB5PHOEGVZ2GI7RVLFAVDJRPTT/action/author_attestation","sign_citation":"https://pith.science/pith/SB5PHOEGVZ2GI7RVLFAVDJRPTT/action/citation_signature","submit_replication":"https://pith.science/pith/SB5PHOEGVZ2GI7RVLFAVDJRPTT/action/replication_record"}},"created_at":"2026-07-05T10:13:04.206822+00:00","updated_at":"2026-07-05T10:13:04.206822+00:00"}