{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PY4FHE3WW7ZST3EBQ4QX5SNUBU","short_pith_number":"pith:PY4FHE3W","schema_version":"1.0","canonical_sha256":"7e38539376b7f329ec8187217ec9b40d2892f19d2bb66e0a1998174223335a26","source":{"kind":"arxiv","id":"2509.06600","version":1},"attestation_state":"computed","paper":{"title":"PAC-Bayesian Generalization Bounds for Graph Convolutional Networks on Inductive Node Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huayi Tang, Yong Liu","submitted_at":"2025-09-08T12:10:54Z","abstract_excerpt":"Graph neural networks (GNNs) have achieved remarkable success in processing graph-structured data across various applications. A critical aspect of real-world graphs is their dynamic nature, where new nodes are continually added and existing connections may change over time. Previous theoretical studies, largely based on the transductive learning framework, fail to adequately model such temporal evolution and structural dynamics. In this paper, we presents a PAC-Bayesian theoretical analysis of graph convolutional networks (GCNs) for inductive node classification, treating nodes as dependent a"},"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":"2509.06600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-08T12:10:54Z","cross_cats_sorted":[],"title_canon_sha256":"489f45c5104653dce6c71ae3ab497537b3dbfb03a36e8e0148a2b07b6d60cdf3","abstract_canon_sha256":"4dff5b63faf9536a49f7ed566c34dd284e4878cd4d85dc6d1bcaceb3bdcbc3a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:39.031783Z","signature_b64":"6x6r/d1jBCLv7888gfP6aaF8zU+Wy2QKc5iisdQtar+oapCf7xlAGtq0tLdzkjvf/8Jwp+Z7Dm009uacG9oGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e38539376b7f329ec8187217ec9b40d2892f19d2bb66e0a1998174223335a26","last_reissued_at":"2026-07-05T12:06:39.031262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:39.031262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAC-Bayesian Generalization Bounds for Graph Convolutional Networks on Inductive Node Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huayi Tang, Yong Liu","submitted_at":"2025-09-08T12:10:54Z","abstract_excerpt":"Graph neural networks (GNNs) have achieved remarkable success in processing graph-structured data across various applications. A critical aspect of real-world graphs is their dynamic nature, where new nodes are continually added and existing connections may change over time. Previous theoretical studies, largely based on the transductive learning framework, fail to adequately model such temporal evolution and structural dynamics. In this paper, we presents a PAC-Bayesian theoretical analysis of graph convolutional networks (GCNs) for inductive node classification, treating nodes as dependent a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06600","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/2509.06600/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":"2509.06600","created_at":"2026-07-05T12:06:39.031322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06600v1","created_at":"2026-07-05T12:06:39.031322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06600","created_at":"2026-07-05T12:06:39.031322+00:00"},{"alias_kind":"pith_short_12","alias_value":"PY4FHE3WW7ZS","created_at":"2026-07-05T12:06:39.031322+00:00"},{"alias_kind":"pith_short_16","alias_value":"PY4FHE3WW7ZST3EB","created_at":"2026-07-05T12:06:39.031322+00:00"},{"alias_kind":"pith_short_8","alias_value":"PY4FHE3W","created_at":"2026-07-05T12:06:39.031322+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/PY4FHE3WW7ZST3EBQ4QX5SNUBU","json":"https://pith.science/pith/PY4FHE3WW7ZST3EBQ4QX5SNUBU.json","graph_json":"https://pith.science/api/pith-number/PY4FHE3WW7ZST3EBQ4QX5SNUBU/graph.json","events_json":"https://pith.science/api/pith-number/PY4FHE3WW7ZST3EBQ4QX5SNUBU/events.json","paper":"https://pith.science/paper/PY4FHE3W"},"agent_actions":{"view_html":"https://pith.science/pith/PY4FHE3WW7ZST3EBQ4QX5SNUBU","download_json":"https://pith.science/pith/PY4FHE3WW7ZST3EBQ4QX5SNUBU.json","view_paper":"https://pith.science/paper/PY4FHE3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06600&json=true","fetch_graph":"https://pith.science/api/pith-number/PY4FHE3WW7ZST3EBQ4QX5SNUBU/graph.json","fetch_events":"https://pith.science/api/pith-number/PY4FHE3WW7ZST3EBQ4QX5SNUBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PY4FHE3WW7ZST3EBQ4QX5SNUBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PY4FHE3WW7ZST3EBQ4QX5SNUBU/action/storage_attestation","attest_author":"https://pith.science/pith/PY4FHE3WW7ZST3EBQ4QX5SNUBU/action/author_attestation","sign_citation":"https://pith.science/pith/PY4FHE3WW7ZST3EBQ4QX5SNUBU/action/citation_signature","submit_replication":"https://pith.science/pith/PY4FHE3WW7ZST3EBQ4QX5SNUBU/action/replication_record"}},"created_at":"2026-07-05T12:06:39.031322+00:00","updated_at":"2026-07-05T12:06:39.031322+00:00"}