{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2LK7APZOK5CIQCPWL7Z3FD4UEE","short_pith_number":"pith:2LK7APZO","schema_version":"1.0","canonical_sha256":"d2d5f03f2e57448809f65ff3b28f94213f1c31f63cd91cde0c9b5e2c759c8646","source":{"kind":"arxiv","id":"2605.25662","version":1},"attestation_state":"computed","paper":{"title":"Closed-Form Node Classification with Exact Graph Unlearning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Gaur, Charu Sharma","submitted_at":"2026-05-25T10:12:43Z","abstract_excerpt":"Graph neural networks for node classification are typically trained by gradient descent over hundreds or thousands of epochs. Recent work has shown that, when properly tuned, classic GCN/SAGE/GAT architectures can match graph transformers on many node-classification benchmarks. We ask a complementary question: how much of this performance can be recovered by deterministic closed-form solvers, and what guarantees does this enable?\n  We introduce a routed closed-form framework selected by adjusted homophily. For assortative graphs, we use SGC-style propagation followed by Ridge regression; for h"},"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":"2605.25662","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T10:12:43Z","cross_cats_sorted":[],"title_canon_sha256":"3c5685555bd8e19cfc4a3de1a446e889498e60d7077811e1178b4d77da76e7d2","abstract_canon_sha256":"699ebf59549956fd22a5d6bb46ea6e3e842283e89c04147822cc7c6cf4ca7b2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:48.897282Z","signature_b64":"NUh0dS6pGv5PCzB4airv1qj5MN+eV5xNlft9E/JdSqmt1KYEm+LX4LZeP50IabcYaTVCMgaF92UsuGVy55hHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2d5f03f2e57448809f65ff3b28f94213f1c31f63cd91cde0c9b5e2c759c8646","last_reissued_at":"2026-05-26T02:04:48.896478Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:48.896478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Closed-Form Node Classification with Exact Graph Unlearning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Gaur, Charu Sharma","submitted_at":"2026-05-25T10:12:43Z","abstract_excerpt":"Graph neural networks for node classification are typically trained by gradient descent over hundreds or thousands of epochs. Recent work has shown that, when properly tuned, classic GCN/SAGE/GAT architectures can match graph transformers on many node-classification benchmarks. We ask a complementary question: how much of this performance can be recovered by deterministic closed-form solvers, and what guarantees does this enable?\n  We introduce a routed closed-form framework selected by adjusted homophily. For assortative graphs, we use SGC-style propagation followed by Ridge regression; for h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25662","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/2605.25662/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":"2605.25662","created_at":"2026-05-26T02:04:48.896613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25662v1","created_at":"2026-05-26T02:04:48.896613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25662","created_at":"2026-05-26T02:04:48.896613+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LK7APZOK5CI","created_at":"2026-05-26T02:04:48.896613+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LK7APZOK5CIQCPW","created_at":"2026-05-26T02:04:48.896613+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LK7APZO","created_at":"2026-05-26T02:04:48.896613+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/2LK7APZOK5CIQCPWL7Z3FD4UEE","json":"https://pith.science/pith/2LK7APZOK5CIQCPWL7Z3FD4UEE.json","graph_json":"https://pith.science/api/pith-number/2LK7APZOK5CIQCPWL7Z3FD4UEE/graph.json","events_json":"https://pith.science/api/pith-number/2LK7APZOK5CIQCPWL7Z3FD4UEE/events.json","paper":"https://pith.science/paper/2LK7APZO"},"agent_actions":{"view_html":"https://pith.science/pith/2LK7APZOK5CIQCPWL7Z3FD4UEE","download_json":"https://pith.science/pith/2LK7APZOK5CIQCPWL7Z3FD4UEE.json","view_paper":"https://pith.science/paper/2LK7APZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25662&json=true","fetch_graph":"https://pith.science/api/pith-number/2LK7APZOK5CIQCPWL7Z3FD4UEE/graph.json","fetch_events":"https://pith.science/api/pith-number/2LK7APZOK5CIQCPWL7Z3FD4UEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LK7APZOK5CIQCPWL7Z3FD4UEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LK7APZOK5CIQCPWL7Z3FD4UEE/action/storage_attestation","attest_author":"https://pith.science/pith/2LK7APZOK5CIQCPWL7Z3FD4UEE/action/author_attestation","sign_citation":"https://pith.science/pith/2LK7APZOK5CIQCPWL7Z3FD4UEE/action/citation_signature","submit_replication":"https://pith.science/pith/2LK7APZOK5CIQCPWL7Z3FD4UEE/action/replication_record"}},"created_at":"2026-05-26T02:04:48.896613+00:00","updated_at":"2026-05-26T02:04:48.896613+00:00"}