{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E4BDYMUCFRTOVVCUB7XHN3JNJQ","short_pith_number":"pith:E4BDYMUC","schema_version":"1.0","canonical_sha256":"27023c32822c66ead4540fee76ed2d4c21b45334dbf7d3f64d3deafde81a6db1","source":{"kind":"arxiv","id":"2405.20445","version":5},"attestation_state":"computed","paper":{"title":"Fully-inductive Node Classification on Arbitrary Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Hesham Mostafa, Jianan Zhao, Jian Tang, Michael Bronstein, Mikhail Galkin, Zhaocheng Zhu","submitted_at":"2024-05-30T19:43:29Z","abstract_excerpt":"One fundamental challenge in graph machine learning is generalizing to new graphs. Many existing methods following the inductive setup can generalize to test graphs with new structures, but assuming the feature and label spaces remain the same as the training ones. This paper introduces a fully-inductive setup, where models should perform inference on arbitrary test graphs with new structures, feature and label spaces. We propose GraphAny as the first attempt at this challenging setup. GraphAny models inference on a new graph as an analytical solution to a LinearGNN, which can be naturally app"},"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":"2405.20445","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T19:43:29Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"02fbff3ffff8ee08f509e57e5ab32c94ae2fa409331f794d3f0c8085703d015c","abstract_canon_sha256":"0d033bafad36226698ed08ad4063000274a18ca2c01e43435391ca7381f52bf3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:52.741334Z","signature_b64":"+Kyyt+BJdN0chPT/vEnhgpz6q14YFE4ROF8/hQfxV7rO9v4XifcWdRxpd7A9KqzbA/JvTKbFVLMSvG890TABBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27023c32822c66ead4540fee76ed2d4c21b45334dbf7d3f64d3deafde81a6db1","last_reissued_at":"2026-07-05T10:45:52.740862Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:52.740862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully-inductive Node Classification on Arbitrary Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Hesham Mostafa, Jianan Zhao, Jian Tang, Michael Bronstein, Mikhail Galkin, Zhaocheng Zhu","submitted_at":"2024-05-30T19:43:29Z","abstract_excerpt":"One fundamental challenge in graph machine learning is generalizing to new graphs. Many existing methods following the inductive setup can generalize to test graphs with new structures, but assuming the feature and label spaces remain the same as the training ones. This paper introduces a fully-inductive setup, where models should perform inference on arbitrary test graphs with new structures, feature and label spaces. We propose GraphAny as the first attempt at this challenging setup. GraphAny models inference on a new graph as an analytical solution to a LinearGNN, which can be naturally app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20445","kind":"arxiv","version":5},"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/2405.20445/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":"2405.20445","created_at":"2026-07-05T10:45:52.740912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20445v5","created_at":"2026-07-05T10:45:52.740912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20445","created_at":"2026-07-05T10:45:52.740912+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4BDYMUCFRTO","created_at":"2026-07-05T10:45:52.740912+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4BDYMUCFRTOVVCU","created_at":"2026-07-05T10:45:52.740912+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4BDYMUC","created_at":"2026-07-05T10:45:52.740912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03315","citing_title":"A Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04244","citing_title":"GraphVec: Cross-Domain Graph Vectorization for Graph-Level Representation Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04834","citing_title":"Bridging Input Feature Spaces Towards Graph Foundation Models","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4BDYMUCFRTOVVCUB7XHN3JNJQ","json":"https://pith.science/pith/E4BDYMUCFRTOVVCUB7XHN3JNJQ.json","graph_json":"https://pith.science/api/pith-number/E4BDYMUCFRTOVVCUB7XHN3JNJQ/graph.json","events_json":"https://pith.science/api/pith-number/E4BDYMUCFRTOVVCUB7XHN3JNJQ/events.json","paper":"https://pith.science/paper/E4BDYMUC"},"agent_actions":{"view_html":"https://pith.science/pith/E4BDYMUCFRTOVVCUB7XHN3JNJQ","download_json":"https://pith.science/pith/E4BDYMUCFRTOVVCUB7XHN3JNJQ.json","view_paper":"https://pith.science/paper/E4BDYMUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20445&json=true","fetch_graph":"https://pith.science/api/pith-number/E4BDYMUCFRTOVVCUB7XHN3JNJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/E4BDYMUCFRTOVVCUB7XHN3JNJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4BDYMUCFRTOVVCUB7XHN3JNJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4BDYMUCFRTOVVCUB7XHN3JNJQ/action/storage_attestation","attest_author":"https://pith.science/pith/E4BDYMUCFRTOVVCUB7XHN3JNJQ/action/author_attestation","sign_citation":"https://pith.science/pith/E4BDYMUCFRTOVVCUB7XHN3JNJQ/action/citation_signature","submit_replication":"https://pith.science/pith/E4BDYMUCFRTOVVCUB7XHN3JNJQ/action/replication_record"}},"created_at":"2026-07-05T10:45:52.740912+00:00","updated_at":"2026-07-05T10:45:52.740912+00:00"}