{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QW3ZCY6NQQWUF7FW5735LC75X7","short_pith_number":"pith:QW3ZCY6N","canonical_record":{"source":{"id":"2305.08048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-14T03:05:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d91d258d02cc0b28cc4e82dfaa51369c930f12410748ae1982044c4cb6c0374c","abstract_canon_sha256":"00e4db568e19e7b870e63b756f189d80e3937552b0b602cc044c1e773693e95f"},"schema_version":"1.0"},"canonical_sha256":"85b79163cd842d42fcb6eff7d58bfdbff568dd7a73741089aec449e273aeccef","source":{"kind":"arxiv","id":"2305.08048","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08048","created_at":"2026-07-05T06:09:57Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08048v1","created_at":"2026-07-05T06:09:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08048","created_at":"2026-07-05T06:09:57Z"},{"alias_kind":"pith_short_12","alias_value":"QW3ZCY6NQQWU","created_at":"2026-07-05T06:09:57Z"},{"alias_kind":"pith_short_16","alias_value":"QW3ZCY6NQQWUF7FW","created_at":"2026-07-05T06:09:57Z"},{"alias_kind":"pith_short_8","alias_value":"QW3ZCY6N","created_at":"2026-07-05T06:09:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QW3ZCY6NQQWUF7FW5735LC75X7","target":"record","payload":{"canonical_record":{"source":{"id":"2305.08048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-14T03:05:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d91d258d02cc0b28cc4e82dfaa51369c930f12410748ae1982044c4cb6c0374c","abstract_canon_sha256":"00e4db568e19e7b870e63b756f189d80e3937552b0b602cc044c1e773693e95f"},"schema_version":"1.0"},"canonical_sha256":"85b79163cd842d42fcb6eff7d58bfdbff568dd7a73741089aec449e273aeccef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:57.341817Z","signature_b64":"tcLzGKi13dMHmMXaBWFubIMuFPOiBNchzi1ghWqyVSC14ZFktYTdMGrggbK2RFd/oiPgedZIVs28H8EngM+nCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85b79163cd842d42fcb6eff7d58bfdbff568dd7a73741089aec449e273aeccef","last_reissued_at":"2026-07-05T06:09:57.341395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:57.341395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.08048","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:09:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"60Rtc8PY3jWekz0PXIcwdkSN1u8FVXBH14S44sHqRUkW35aJJZnBKFtl5+p6mjC6NDfWCgdCAMYZe7OC5MDIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:21:01.462779Z"},"content_sha256":"a9ec15bf897a908f0648e34c9a04493a08b45180b478fc25dbf48a8902d773b2","schema_version":"1.0","event_id":"sha256:a9ec15bf897a908f0648e34c9a04493a08b45180b478fc25dbf48a8902d773b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QW3ZCY6NQQWUF7FW5735LC75X7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Understanding the Generalization of Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huayi Tang, Yong Liu","submitted_at":"2023-05-14T03:05:14Z","abstract_excerpt":"Graph neural networks (GNNs) are the most widely adopted model in graph-structured data oriented learning and representation. Despite their extraordinary success in real-world applications, understanding their working mechanism by theory is still on primary stage. In this paper, we move towards this goal from the perspective of generalization. To be specific, we first establish high probability bounds of generalization gap and gradients in transductive learning with consideration of stochastic optimization. After that, we provide high probability bounds of generalization gap for popular GNNs. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08048","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/2305.08048/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:09:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XF57xf8ePnJOE4dAvTGlCBeE3FIFdHy/vw6pbg1Y6ekck60gYtOp0HL9HGXAMfuBjapNVu68ASGN7zAJKas0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:21:01.463614Z"},"content_sha256":"06a4ab6ad633bc1a6ed3d9baf31c0e3f57cf261626e8739d5b0eb823cd087b5a","schema_version":"1.0","event_id":"sha256:06a4ab6ad633bc1a6ed3d9baf31c0e3f57cf261626e8739d5b0eb823cd087b5a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QW3ZCY6NQQWUF7FW5735LC75X7/bundle.json","state_url":"https://pith.science/pith/QW3ZCY6NQQWUF7FW5735LC75X7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QW3ZCY6NQQWUF7FW5735LC75X7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T23:21:01Z","links":{"resolver":"https://pith.science/pith/QW3ZCY6NQQWUF7FW5735LC75X7","bundle":"https://pith.science/pith/QW3ZCY6NQQWUF7FW5735LC75X7/bundle.json","state":"https://pith.science/pith/QW3ZCY6NQQWUF7FW5735LC75X7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QW3ZCY6NQQWUF7FW5735LC75X7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QW3ZCY6NQQWUF7FW5735LC75X7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"00e4db568e19e7b870e63b756f189d80e3937552b0b602cc044c1e773693e95f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-14T03:05:14Z","title_canon_sha256":"d91d258d02cc0b28cc4e82dfaa51369c930f12410748ae1982044c4cb6c0374c"},"schema_version":"1.0","source":{"id":"2305.08048","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08048","created_at":"2026-07-05T06:09:57Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08048v1","created_at":"2026-07-05T06:09:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08048","created_at":"2026-07-05T06:09:57Z"},{"alias_kind":"pith_short_12","alias_value":"QW3ZCY6NQQWU","created_at":"2026-07-05T06:09:57Z"},{"alias_kind":"pith_short_16","alias_value":"QW3ZCY6NQQWUF7FW","created_at":"2026-07-05T06:09:57Z"},{"alias_kind":"pith_short_8","alias_value":"QW3ZCY6N","created_at":"2026-07-05T06:09:57Z"}],"graph_snapshots":[{"event_id":"sha256:06a4ab6ad633bc1a6ed3d9baf31c0e3f57cf261626e8739d5b0eb823cd087b5a","target":"graph","created_at":"2026-07-05T06:09:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.08048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph neural networks (GNNs) are the most widely adopted model in graph-structured data oriented learning and representation. Despite their extraordinary success in real-world applications, understanding their working mechanism by theory is still on primary stage. In this paper, we move towards this goal from the perspective of generalization. To be specific, we first establish high probability bounds of generalization gap and gradients in transductive learning with consideration of stochastic optimization. After that, we provide high probability bounds of generalization gap for popular GNNs. ","authors_text":"Huayi Tang, Yong Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-14T03:05:14Z","title":"Towards Understanding the Generalization of Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08048","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a9ec15bf897a908f0648e34c9a04493a08b45180b478fc25dbf48a8902d773b2","target":"record","created_at":"2026-07-05T06:09:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"00e4db568e19e7b870e63b756f189d80e3937552b0b602cc044c1e773693e95f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-14T03:05:14Z","title_canon_sha256":"d91d258d02cc0b28cc4e82dfaa51369c930f12410748ae1982044c4cb6c0374c"},"schema_version":"1.0","source":{"id":"2305.08048","kind":"arxiv","version":1}},"canonical_sha256":"85b79163cd842d42fcb6eff7d58bfdbff568dd7a73741089aec449e273aeccef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85b79163cd842d42fcb6eff7d58bfdbff568dd7a73741089aec449e273aeccef","first_computed_at":"2026-07-05T06:09:57.341395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:57.341395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tcLzGKi13dMHmMXaBWFubIMuFPOiBNchzi1ghWqyVSC14ZFktYTdMGrggbK2RFd/oiPgedZIVs28H8EngM+nCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:57.341817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.08048","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9ec15bf897a908f0648e34c9a04493a08b45180b478fc25dbf48a8902d773b2","sha256:06a4ab6ad633bc1a6ed3d9baf31c0e3f57cf261626e8739d5b0eb823cd087b5a"],"state_sha256":"92b94ae876739124b80ceb55b6f9e5cca51aa20e9cc1f4515188ea0c69608fdb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ua6Uq3r333h9p+j4fNWbITev4YSD/FM9GWGEEl+cCW0c9JDLKhu2wyF1SvmxlLZBQF002uX4LLja7ixJiQqSBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:21:01.469183Z","bundle_sha256":"811eaf3b6f8d4d7e3b6a1e31006138f28bfe7f3c5697b8acb1abe32e1d18683c"}}