{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:76OWLDLC5MSYF6VDUVRZU4MZVL","short_pith_number":"pith:76OWLDLC","canonical_record":{"source":{"id":"2505.11298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T14:28:34Z","cross_cats_sorted":[],"title_canon_sha256":"dbabc673199d0dc8db1253529ab98a9023fcfe28203326a9311cec38d3091ed6","abstract_canon_sha256":"d7e6342b738bbfcbb86bb33179aad872e02943bb233ac4f61aee7d928c5cbced"},"schema_version":"1.0"},"canonical_sha256":"ff9d658d62eb2582faa3a5639a7199aac8a4ce36e2f0cc8d8ffde06021e2f1ff","source":{"kind":"arxiv","id":"2505.11298","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11298","created_at":"2026-07-05T11:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11298v1","created_at":"2026-07-05T11:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11298","created_at":"2026-07-05T11:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"76OWLDLC5MSY","created_at":"2026-07-05T11:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"76OWLDLC5MSYF6VD","created_at":"2026-07-05T11:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"76OWLDLC","created_at":"2026-07-05T11:04:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:76OWLDLC5MSYF6VDUVRZU4MZVL","target":"record","payload":{"canonical_record":{"source":{"id":"2505.11298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T14:28:34Z","cross_cats_sorted":[],"title_canon_sha256":"dbabc673199d0dc8db1253529ab98a9023fcfe28203326a9311cec38d3091ed6","abstract_canon_sha256":"d7e6342b738bbfcbb86bb33179aad872e02943bb233ac4f61aee7d928c5cbced"},"schema_version":"1.0"},"canonical_sha256":"ff9d658d62eb2582faa3a5639a7199aac8a4ce36e2f0cc8d8ffde06021e2f1ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:14.022739Z","signature_b64":"1ogF2XZesVDfKkA8XYlt2QuhvPO35o8F/u1yIg++1bP+R9Qe+hsjtcpNoNyZJ0YBng+WdTkfBnRxeuDgo4ukDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff9d658d62eb2582faa3a5639a7199aac8a4ce36e2f0cc8d8ffde06021e2f1ff","last_reissued_at":"2026-07-05T11:04:14.022171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:14.022171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.11298","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":"2026-07-05T11:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7hSRTgivZMBSwUA7PC8lMA18C+0WoSE4dqO16rc1xFUHsM24DEv+lB5oJK9yG6Mh5gHsA7LlwRcZo9zgMy5nCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:33:13.467129Z"},"content_sha256":"0cb79e2afa1ec8b8172386364a624546beb3a41302b60eb6e1584645699157d6","schema_version":"1.0","event_id":"sha256:0cb79e2afa1ec8b8172386364a624546beb3a41302b60eb6e1584645699157d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:76OWLDLC5MSYF6VDUVRZU4MZVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph Representational Learning: When Does More Expressivity Hurt Generalization?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fabian Jogl, Gitta Kutyniok, Johannes F. Lutzeyer, Raffaele Paolino, Sohir Maskey","submitted_at":"2025-05-16T14:28:34Z","abstract_excerpt":"Graph Neural Networks (GNNs) are powerful tools for learning on structured data, yet the relationship between their expressivity and predictive performance remains unclear. We introduce a family of premetrics that capture different degrees of structural similarity between graphs and relate these similarities to generalization, and consequently, the performance of expressive GNNs. By considering a setting where graph labels are correlated with structural features, we derive generalization bounds that depend on the distance between training and test graphs, model complexity, and training set siz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11298","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/2505.11298/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":"2026-07-05T11:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WFWrtJOH6+QuRNLw9GSylDpzKC3CMGskeuEf8eUwRoCheSB7LwilNv7M0BP0eRO8uIUajflsLsIBuX4zCWaRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:33:13.467596Z"},"content_sha256":"43869a0f8bc6c187ada0f9000516284871cb1a18b2e4e5d6af63f0e83a727cac","schema_version":"1.0","event_id":"sha256:43869a0f8bc6c187ada0f9000516284871cb1a18b2e4e5d6af63f0e83a727cac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/76OWLDLC5MSYF6VDUVRZU4MZVL/bundle.json","state_url":"https://pith.science/pith/76OWLDLC5MSYF6VDUVRZU4MZVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/76OWLDLC5MSYF6VDUVRZU4MZVL/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":"2026-08-05T11:33:13Z","links":{"resolver":"https://pith.science/pith/76OWLDLC5MSYF6VDUVRZU4MZVL","bundle":"https://pith.science/pith/76OWLDLC5MSYF6VDUVRZU4MZVL/bundle.json","state":"https://pith.science/pith/76OWLDLC5MSYF6VDUVRZU4MZVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/76OWLDLC5MSYF6VDUVRZU4MZVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:76OWLDLC5MSYF6VDUVRZU4MZVL","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":"d7e6342b738bbfcbb86bb33179aad872e02943bb233ac4f61aee7d928c5cbced","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T14:28:34Z","title_canon_sha256":"dbabc673199d0dc8db1253529ab98a9023fcfe28203326a9311cec38d3091ed6"},"schema_version":"1.0","source":{"id":"2505.11298","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11298","created_at":"2026-07-05T11:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11298v1","created_at":"2026-07-05T11:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11298","created_at":"2026-07-05T11:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"76OWLDLC5MSY","created_at":"2026-07-05T11:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"76OWLDLC5MSYF6VD","created_at":"2026-07-05T11:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"76OWLDLC","created_at":"2026-07-05T11:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:43869a0f8bc6c187ada0f9000516284871cb1a18b2e4e5d6af63f0e83a727cac","target":"graph","created_at":"2026-07-05T11:04:14Z","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/2505.11298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) are powerful tools for learning on structured data, yet the relationship between their expressivity and predictive performance remains unclear. We introduce a family of premetrics that capture different degrees of structural similarity between graphs and relate these similarities to generalization, and consequently, the performance of expressive GNNs. By considering a setting where graph labels are correlated with structural features, we derive generalization bounds that depend on the distance between training and test graphs, model complexity, and training set siz","authors_text":"Fabian Jogl, Gitta Kutyniok, Johannes F. Lutzeyer, Raffaele Paolino, Sohir Maskey","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T14:28:34Z","title":"Graph Representational Learning: When Does More Expressivity Hurt Generalization?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11298","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":"sha256:0cb79e2afa1ec8b8172386364a624546beb3a41302b60eb6e1584645699157d6","target":"record","created_at":"2026-07-05T11:04:14Z","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":"d7e6342b738bbfcbb86bb33179aad872e02943bb233ac4f61aee7d928c5cbced","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T14:28:34Z","title_canon_sha256":"dbabc673199d0dc8db1253529ab98a9023fcfe28203326a9311cec38d3091ed6"},"schema_version":"1.0","source":{"id":"2505.11298","kind":"arxiv","version":1}},"canonical_sha256":"ff9d658d62eb2582faa3a5639a7199aac8a4ce36e2f0cc8d8ffde06021e2f1ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff9d658d62eb2582faa3a5639a7199aac8a4ce36e2f0cc8d8ffde06021e2f1ff","first_computed_at":"2026-07-05T11:04:14.022171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:14.022171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1ogF2XZesVDfKkA8XYlt2QuhvPO35o8F/u1yIg++1bP+R9Qe+hsjtcpNoNyZJ0YBng+WdTkfBnRxeuDgo4ukDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:14.022739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11298","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cb79e2afa1ec8b8172386364a624546beb3a41302b60eb6e1584645699157d6","sha256:43869a0f8bc6c187ada0f9000516284871cb1a18b2e4e5d6af63f0e83a727cac"],"state_sha256":"8df0e0981762e3691785ef2473230ef2abb6578ba58618ae3c9d8b2e05a371e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AF4qAbdWG7ukYL5GrmbzLpsggjnPz1OGIg5q/SYo6R7IAWfaw/cUUphLWs3DBjioww7EUKjKR3rKAH4DSdseCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:33:13.479775Z","bundle_sha256":"875930f6faf9cceb35c1ff7f0abe3753d9d4fda690e6cd1acc353dd1c5d37371"}}