{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P6GYH5X34QS47XCR5W3H6AASL5","short_pith_number":"pith:P6GYH5X3","canonical_record":{"source":{"id":"2503.15650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T19:04:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7969b2c644fe510322570a2b8c6ab17c8e17a3bd96ee4072a12fef98a41e30ac","abstract_canon_sha256":"cda62dc30d4290198fed0a0eb785f62e7c3cee91ce39c796098b46911ceb3495"},"schema_version":"1.0"},"canonical_sha256":"7f8d83f6fbe425cfdc51edb67f00125f7a57f306cd5311c285c45bb4c6616265","source":{"kind":"arxiv","id":"2503.15650","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15650","created_at":"2026-07-05T10:35:55Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15650v1","created_at":"2026-07-05T10:35:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15650","created_at":"2026-07-05T10:35:55Z"},{"alias_kind":"pith_short_12","alias_value":"P6GYH5X34QS4","created_at":"2026-07-05T10:35:55Z"},{"alias_kind":"pith_short_16","alias_value":"P6GYH5X34QS47XCR","created_at":"2026-07-05T10:35:55Z"},{"alias_kind":"pith_short_8","alias_value":"P6GYH5X3","created_at":"2026-07-05T10:35:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P6GYH5X34QS47XCR5W3H6AASL5","target":"record","payload":{"canonical_record":{"source":{"id":"2503.15650","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T19:04:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"7969b2c644fe510322570a2b8c6ab17c8e17a3bd96ee4072a12fef98a41e30ac","abstract_canon_sha256":"cda62dc30d4290198fed0a0eb785f62e7c3cee91ce39c796098b46911ceb3495"},"schema_version":"1.0"},"canonical_sha256":"7f8d83f6fbe425cfdc51edb67f00125f7a57f306cd5311c285c45bb4c6616265","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:55.039695Z","signature_b64":"NZ/GZg6Xx0ER/lYZy47hyuWmo+mZ6Ppu/7ePe64PDIgZgmHymlekQ/7l9JoY0HoAc/GVK7vElHOTthsFbX2XAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f8d83f6fbe425cfdc51edb67f00125f7a57f306cd5311c285c45bb4c6616265","last_reissued_at":"2026-07-05T10:35:55.039191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:55.039191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.15650","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":"2026-07-05T10:35:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"38aJHbyqirqmVWGi0ZYrtzDL3pFi1MQ8A2+3qfdmmzOF3WB5vlPl3/Jl252i9n/7ruCtDoqshyYfRFDmcKJhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:38:37.782271Z"},"content_sha256":"b51c680ff4ba490b2cfc0acfe27d5fa84a98aea6f9d64da89b94dcc084c96f11","schema_version":"1.0","event_id":"sha256:b51c680ff4ba490b2cfc0acfe27d5fa84a98aea6f9d64da89b94dcc084c96f11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P6GYH5X34QS47XCR5W3H6AASL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Survey on Generalization Theory for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonis Vasileiou, Christopher Morris, Ron Levie, Stefanie Jegelka","submitted_at":"2025-03-19T19:04:24Z","abstract_excerpt":"Message-passing graph neural networks (MPNNs) have emerged as the leading approach for machine learning on graphs, attracting significant attention in recent years. While a large set of works explored the expressivity of MPNNs, i.e., their ability to separate graphs and approximate functions over them, comparatively less attention has been directed toward investigating their generalization abilities, i.e., making meaningful predictions beyond the training data. Here, we systematically review the existing literature on the generalization abilities of MPNNs. We analyze the strengths and limitati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15650","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/2503.15650/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":"2026-07-05T10:35:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TFumVwqEW5pNJzNvZXTEnQ4g0RjWwyOagfggepLYTE2IMu+6MaznKWdcNJXOVMDN8VGOL7KOBbWaZ/mcncwJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:38:37.783113Z"},"content_sha256":"7f71331c08a839f65efe5f5b14995ab3cdf26d31e4ea7c09d2721ffdafde8fee","schema_version":"1.0","event_id":"sha256:7f71331c08a839f65efe5f5b14995ab3cdf26d31e4ea7c09d2721ffdafde8fee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P6GYH5X34QS47XCR5W3H6AASL5/bundle.json","state_url":"https://pith.science/pith/P6GYH5X34QS47XCR5W3H6AASL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P6GYH5X34QS47XCR5W3H6AASL5/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":"2026-08-20T12:38:37Z","links":{"resolver":"https://pith.science/pith/P6GYH5X34QS47XCR5W3H6AASL5","bundle":"https://pith.science/pith/P6GYH5X34QS47XCR5W3H6AASL5/bundle.json","state":"https://pith.science/pith/P6GYH5X34QS47XCR5W3H6AASL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P6GYH5X34QS47XCR5W3H6AASL5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P6GYH5X34QS47XCR5W3H6AASL5","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":"cda62dc30d4290198fed0a0eb785f62e7c3cee91ce39c796098b46911ceb3495","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T19:04:24Z","title_canon_sha256":"7969b2c644fe510322570a2b8c6ab17c8e17a3bd96ee4072a12fef98a41e30ac"},"schema_version":"1.0","source":{"id":"2503.15650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15650","created_at":"2026-07-05T10:35:55Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15650v1","created_at":"2026-07-05T10:35:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15650","created_at":"2026-07-05T10:35:55Z"},{"alias_kind":"pith_short_12","alias_value":"P6GYH5X34QS4","created_at":"2026-07-05T10:35:55Z"},{"alias_kind":"pith_short_16","alias_value":"P6GYH5X34QS47XCR","created_at":"2026-07-05T10:35:55Z"},{"alias_kind":"pith_short_8","alias_value":"P6GYH5X3","created_at":"2026-07-05T10:35:55Z"}],"graph_snapshots":[{"event_id":"sha256:7f71331c08a839f65efe5f5b14995ab3cdf26d31e4ea7c09d2721ffdafde8fee","target":"graph","created_at":"2026-07-05T10:35:55Z","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/2503.15650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Message-passing graph neural networks (MPNNs) have emerged as the leading approach for machine learning on graphs, attracting significant attention in recent years. While a large set of works explored the expressivity of MPNNs, i.e., their ability to separate graphs and approximate functions over them, comparatively less attention has been directed toward investigating their generalization abilities, i.e., making meaningful predictions beyond the training data. Here, we systematically review the existing literature on the generalization abilities of MPNNs. We analyze the strengths and limitati","authors_text":"Antonis Vasileiou, Christopher Morris, Ron Levie, Stefanie Jegelka","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T19:04:24Z","title":"Survey on Generalization Theory for Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15650","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:b51c680ff4ba490b2cfc0acfe27d5fa84a98aea6f9d64da89b94dcc084c96f11","target":"record","created_at":"2026-07-05T10:35:55Z","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":"cda62dc30d4290198fed0a0eb785f62e7c3cee91ce39c796098b46911ceb3495","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-19T19:04:24Z","title_canon_sha256":"7969b2c644fe510322570a2b8c6ab17c8e17a3bd96ee4072a12fef98a41e30ac"},"schema_version":"1.0","source":{"id":"2503.15650","kind":"arxiv","version":1}},"canonical_sha256":"7f8d83f6fbe425cfdc51edb67f00125f7a57f306cd5311c285c45bb4c6616265","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f8d83f6fbe425cfdc51edb67f00125f7a57f306cd5311c285c45bb4c6616265","first_computed_at":"2026-07-05T10:35:55.039191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:55.039191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NZ/GZg6Xx0ER/lYZy47hyuWmo+mZ6Ppu/7ePe64PDIgZgmHymlekQ/7l9JoY0HoAc/GVK7vElHOTthsFbX2XAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:55.039695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b51c680ff4ba490b2cfc0acfe27d5fa84a98aea6f9d64da89b94dcc084c96f11","sha256:7f71331c08a839f65efe5f5b14995ab3cdf26d31e4ea7c09d2721ffdafde8fee"],"state_sha256":"3ec2f79026fa5ae744e63564a1bcb8c2e4dea0587f0ca66e564c2b6b958220f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qZ6jATfoxEBSsblFJatkHRhj4h6h0B7JnpbaDrSMCxqWgsTMX8fonzjBYnwDjUQxuSPqi9vou5qOySg71aKxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T12:38:37.794426Z","bundle_sha256":"0539a957e2998528d3cc3a412feba1ee40df591f85672c22e1834bde836b72e2"}}