{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PELEPJ77NTCFYD6ODMG525AGIM","short_pith_number":"pith:PELEPJ77","canonical_record":{"source":{"id":"1905.06018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T08:11:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0cf6988fa433869b82353929d16046f4be4078a6a91d38f11bb012eb3446396e","abstract_canon_sha256":"d0cb3a82dbc0713c5a35c12896b3925aacf9ba34138d14f20a13b23a80d3582c"},"schema_version":"1.0"},"canonical_sha256":"791647a7ff6cc45c0fce1b0ddd7406433ec1ac6e96a42db7c57106be1d2715a3","source":{"kind":"arxiv","id":"1905.06018","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06018","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06018v1","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06018","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"PELEPJ77NTCF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PELEPJ77NTCFYD6O","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PELEPJ77","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PELEPJ77NTCFYD6ODMG525AGIM","target":"record","payload":{"canonical_record":{"source":{"id":"1905.06018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T08:11:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0cf6988fa433869b82353929d16046f4be4078a6a91d38f11bb012eb3446396e","abstract_canon_sha256":"d0cb3a82dbc0713c5a35c12896b3925aacf9ba34138d14f20a13b23a80d3582c"},"schema_version":"1.0"},"canonical_sha256":"791647a7ff6cc45c0fce1b0ddd7406433ec1ac6e96a42db7c57106be1d2715a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:07.726919Z","signature_b64":"Ro6VRo+3aD2voGs8uYIDKHcCMq/xXOoUERwrr2fiwNnoZXs0QJcz7iYgu7DDhaeaGJCFF/CajAmLELEe16vgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"791647a7ff6cc45c0fce1b0ddd7406433ec1ac6e96a42db7c57106be1d2715a3","last_reissued_at":"2026-05-17T23:46:07.726298Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:07.726298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.06018","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":"2026-05-17T23:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qxJ6wfuB8Mw3QZwWtBa8ywwBVDhHJRs69QsNOO7ZslpX9cdXLDUodtnhtypgVydJ0LqGF3yejQqzOciwI7RnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:31:00.882487Z"},"content_sha256":"07ae3d0ffe64391936dfee8b8d14e12401ab32a1514fac3034545e4d12c011ac","schema_version":"1.0","event_id":"sha256:07ae3d0ffe64391936dfee8b8d14e12401ab32a1514fac3034545e4d12c011ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PELEPJ77NTCFYD6ODMG525AGIM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Graph Neural Networks Go \"Online\"? An Analysis of Pretraining and Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ansgar Scherp, Iacopo Vagliano, Lukas Galke","submitted_at":"2019-05-15T08:11:54Z","abstract_excerpt":"Large-scale graph data in real-world applications is often not static but dynamic, i. e., new nodes and edges appear over time. Current graph convolution approaches are promising, especially, when all the graph's nodes and edges are available during training. When unseen nodes and edges are inserted after training, it is not yet evaluated whether up-training or re-training from scratch is preferable. We construct an experimental setup, in which we insert previously unseen nodes and edges after training and conduct a limited amount of inference epochs. In this setup, we compare adapting pretrai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06018","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":""},"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":"2026-05-17T23:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BPjqgQSBrDVbVAUpapFpKvt4SVLpHVcdkV8kKvJv90hCAgEZlqNsIkgY+fBo8S5KdoctdRRjCX8HSmqBbr0kBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:31:00.883183Z"},"content_sha256":"c89629652a88d824941f0a97e1b2210631ef977d3bca54f83e82c635ef6a70d4","schema_version":"1.0","event_id":"sha256:c89629652a88d824941f0a97e1b2210631ef977d3bca54f83e82c635ef6a70d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PELEPJ77NTCFYD6ODMG525AGIM/bundle.json","state_url":"https://pith.science/pith/PELEPJ77NTCFYD6ODMG525AGIM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PELEPJ77NTCFYD6ODMG525AGIM/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":"2026-05-31T22:31:00Z","links":{"resolver":"https://pith.science/pith/PELEPJ77NTCFYD6ODMG525AGIM","bundle":"https://pith.science/pith/PELEPJ77NTCFYD6ODMG525AGIM/bundle.json","state":"https://pith.science/pith/PELEPJ77NTCFYD6ODMG525AGIM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PELEPJ77NTCFYD6ODMG525AGIM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PELEPJ77NTCFYD6ODMG525AGIM","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":"d0cb3a82dbc0713c5a35c12896b3925aacf9ba34138d14f20a13b23a80d3582c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T08:11:54Z","title_canon_sha256":"0cf6988fa433869b82353929d16046f4be4078a6a91d38f11bb012eb3446396e"},"schema_version":"1.0","source":{"id":"1905.06018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06018","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06018v1","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06018","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"PELEPJ77NTCF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PELEPJ77NTCFYD6O","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PELEPJ77","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:c89629652a88d824941f0a97e1b2210631ef977d3bca54f83e82c635ef6a70d4","target":"graph","created_at":"2026-05-17T23:46:07Z","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"},"paper":{"abstract_excerpt":"Large-scale graph data in real-world applications is often not static but dynamic, i. e., new nodes and edges appear over time. Current graph convolution approaches are promising, especially, when all the graph's nodes and edges are available during training. When unseen nodes and edges are inserted after training, it is not yet evaluated whether up-training or re-training from scratch is preferable. We construct an experimental setup, in which we insert previously unseen nodes and edges after training and conduct a limited amount of inference epochs. In this setup, we compare adapting pretrai","authors_text":"Ansgar Scherp, Iacopo Vagliano, Lukas Galke","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T08:11:54Z","title":"Can Graph Neural Networks Go \"Online\"? An Analysis of Pretraining and Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06018","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":"sha256:07ae3d0ffe64391936dfee8b8d14e12401ab32a1514fac3034545e4d12c011ac","target":"record","created_at":"2026-05-17T23:46:07Z","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":"d0cb3a82dbc0713c5a35c12896b3925aacf9ba34138d14f20a13b23a80d3582c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T08:11:54Z","title_canon_sha256":"0cf6988fa433869b82353929d16046f4be4078a6a91d38f11bb012eb3446396e"},"schema_version":"1.0","source":{"id":"1905.06018","kind":"arxiv","version":1}},"canonical_sha256":"791647a7ff6cc45c0fce1b0ddd7406433ec1ac6e96a42db7c57106be1d2715a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"791647a7ff6cc45c0fce1b0ddd7406433ec1ac6e96a42db7c57106be1d2715a3","first_computed_at":"2026-05-17T23:46:07.726298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:07.726298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ro6VRo+3aD2voGs8uYIDKHcCMq/xXOoUERwrr2fiwNnoZXs0QJcz7iYgu7DDhaeaGJCFF/CajAmLELEe16vgDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:07.726919Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.06018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07ae3d0ffe64391936dfee8b8d14e12401ab32a1514fac3034545e4d12c011ac","sha256:c89629652a88d824941f0a97e1b2210631ef977d3bca54f83e82c635ef6a70d4"],"state_sha256":"849c1fe93084306ad37a34b3554c6e1df453b47bbc5dc5b28191401cb0147247"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"laeYdKvNpKJh3b4kpVmCkQ94rrdQZ8bhENvmLUHeEBf/FP4m1LFqIIgV7dpFv7PaEPciAb3yv/gUw9md4DQVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T22:31:00.887012Z","bundle_sha256":"222c8c1dd36ca7b0032eca4cfb4d5429abe039b82e9826be93633d535f96ca21"}}