{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S3VSFYR3Q6T7S2EBXAPQSB4TSY","short_pith_number":"pith:S3VSFYR3","schema_version":"1.0","canonical_sha256":"96eb22e23b87a7f96881b81f090793961c2c4b1d29b843462f2424d68d12ecd9","source":{"kind":"arxiv","id":"2410.09708","version":2},"attestation_state":"computed","paper":{"title":"Control the GNN: Utilizing Neural Controller with Lyapunov Stability for Test-Time Feature Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feng Ji, Hongbin Wang, Jielong Yang, Linbo Xie, Rui Ding","submitted_at":"2024-10-13T03:34:19Z","abstract_excerpt":"The performance of graph neural networks (GNNs) is susceptible to discrepancies between training and testing sample distributions. Prior studies have attempted to mitigating the impact of distribution shift by reconstructing node features during the testing phase without modifying the model parameters. However, these approaches lack theoretical analysis of the proximity between predictions and ground truth at test time. In this paper, we propose a novel node feature reconstruction method grounded in Lyapunov stability theory. Specifically, we model the GNN as a control system during the testin"},"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":"2410.09708","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-13T03:34:19Z","cross_cats_sorted":[],"title_canon_sha256":"705d4c262d99e8223641d48f749dd2276cafe48fab2199a9c7a320447c16aa7d","abstract_canon_sha256":"fd663014d530c56685a713942bfb72870f14fa411046efc344a368d05ad2b679"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:09.551277Z","signature_b64":"gDFjyqxK73+pFmwYRTTyDEBEmS8InyDlhzMbaHY9YjWocwxm39oq6gyi9e2p8dBWv4NZxi9vYCn7Vrx58iGKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96eb22e23b87a7f96881b81f090793961c2c4b1d29b843462f2424d68d12ecd9","last_reissued_at":"2026-07-05T10:50:09.550851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:09.550851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Control the GNN: Utilizing Neural Controller with Lyapunov Stability for Test-Time Feature Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feng Ji, Hongbin Wang, Jielong Yang, Linbo Xie, Rui Ding","submitted_at":"2024-10-13T03:34:19Z","abstract_excerpt":"The performance of graph neural networks (GNNs) is susceptible to discrepancies between training and testing sample distributions. Prior studies have attempted to mitigating the impact of distribution shift by reconstructing node features during the testing phase without modifying the model parameters. However, these approaches lack theoretical analysis of the proximity between predictions and ground truth at test time. In this paper, we propose a novel node feature reconstruction method grounded in Lyapunov stability theory. Specifically, we model the GNN as a control system during the testin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09708","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/2410.09708/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":"2410.09708","created_at":"2026-07-05T10:50:09.550905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09708v2","created_at":"2026-07-05T10:50:09.550905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09708","created_at":"2026-07-05T10:50:09.550905+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3VSFYR3Q6T7","created_at":"2026-07-05T10:50:09.550905+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3VSFYR3Q6T7S2EB","created_at":"2026-07-05T10:50:09.550905+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3VSFYR3","created_at":"2026-07-05T10:50:09.550905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15195","citing_title":"Feature Construction Using Network Control Theory and Rank Encoding for Graph Machine Learning","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3VSFYR3Q6T7S2EBXAPQSB4TSY","json":"https://pith.science/pith/S3VSFYR3Q6T7S2EBXAPQSB4TSY.json","graph_json":"https://pith.science/api/pith-number/S3VSFYR3Q6T7S2EBXAPQSB4TSY/graph.json","events_json":"https://pith.science/api/pith-number/S3VSFYR3Q6T7S2EBXAPQSB4TSY/events.json","paper":"https://pith.science/paper/S3VSFYR3"},"agent_actions":{"view_html":"https://pith.science/pith/S3VSFYR3Q6T7S2EBXAPQSB4TSY","download_json":"https://pith.science/pith/S3VSFYR3Q6T7S2EBXAPQSB4TSY.json","view_paper":"https://pith.science/paper/S3VSFYR3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09708&json=true","fetch_graph":"https://pith.science/api/pith-number/S3VSFYR3Q6T7S2EBXAPQSB4TSY/graph.json","fetch_events":"https://pith.science/api/pith-number/S3VSFYR3Q6T7S2EBXAPQSB4TSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3VSFYR3Q6T7S2EBXAPQSB4TSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3VSFYR3Q6T7S2EBXAPQSB4TSY/action/storage_attestation","attest_author":"https://pith.science/pith/S3VSFYR3Q6T7S2EBXAPQSB4TSY/action/author_attestation","sign_citation":"https://pith.science/pith/S3VSFYR3Q6T7S2EBXAPQSB4TSY/action/citation_signature","submit_replication":"https://pith.science/pith/S3VSFYR3Q6T7S2EBXAPQSB4TSY/action/replication_record"}},"created_at":"2026-07-05T10:50:09.550905+00:00","updated_at":"2026-07-05T10:50:09.550905+00:00"}