{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VYX65YAHD43PDMFXKTZMZHGYDM","short_pith_number":"pith:VYX65YAH","canonical_record":{"source":{"id":"1905.13728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T17:25:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"962422f3e77486c6d335fbec4f25a89edfe91cc5da38bc040477c1987a5445ee","abstract_canon_sha256":"1b18dd16bbf1d40483ae1ff8ba719715cdd58811031e1650f9ada42aef622b4a"},"schema_version":"1.0"},"canonical_sha256":"ae2feee0071f36f1b0b754f2cc9cd81b08657cb9990a800b67c02a6271a819ad","source":{"kind":"arxiv","id":"1905.13728","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13728","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13728v1","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13728","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"VYX65YAHD43P","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VYX65YAHD43PDMFX","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VYX65YAH","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VYX65YAHD43PDMFXKTZMZHGYDM","target":"record","payload":{"canonical_record":{"source":{"id":"1905.13728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T17:25:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"962422f3e77486c6d335fbec4f25a89edfe91cc5da38bc040477c1987a5445ee","abstract_canon_sha256":"1b18dd16bbf1d40483ae1ff8ba719715cdd58811031e1650f9ada42aef622b4a"},"schema_version":"1.0"},"canonical_sha256":"ae2feee0071f36f1b0b754f2cc9cd81b08657cb9990a800b67c02a6271a819ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:34.099071Z","signature_b64":"EsUdF2uPL0a1bKvG/hzG9fq4nfSM0qpiv7IaHtTCv6aDJs3otf68OV3xfwtGzWsmLDNBw3Htze53UwwD88T9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae2feee0071f36f1b0b754f2cc9cd81b08657cb9990a800b67c02a6271a819ad","last_reissued_at":"2026-05-17T23:44:34.098509Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:34.098509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.13728","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":"2026-05-17T23:44:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9HITVU8twvGZMDffOSv/KrfGbthz612eg/0ZVyf1vFrpbhaGvzHB671Qbxi5JH6UdIYnOyA2dJcoiUK6AomkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T08:16:38.889236Z"},"content_sha256":"3ff8889be43891deae0ea5b6ec45631627ffcce2d653d79fe03a8c07363697dd","schema_version":"1.0","event_id":"sha256:3ff8889be43891deae0ea5b6ec45631627ffcce2d653d79fe03a8c07363697dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VYX65YAHD43PDMFXKTZMZHGYDM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-Training Graph Neural Networks for Generic Structural Feature Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Changjun Fan, Kai-Wei Chang, Ting Chen, Yizhou Sun, Ziniu Hu","submitted_at":"2019-05-31T17:25:29Z","abstract_excerpt":"Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible for some applications. To tackle this problem, we propose a pre-training framework that captures generic graph structural information that is transferable across tasks. Our framework can leverage the following three tasks: 1) denoising link reconstruction, 2) centrality score ranking, and 3) cluster preserving. The pre-training procedure can be conducted pu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13728","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":"2026-05-17T23:44:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1I82P4iQaM1UOMyCdpMlA6VCcwZGes2T/GMDzqDuS6dJLcByR2vuVGNr6GhV+zqC5r2MriXW8QtZiOkL37vYAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T08:16:38.889657Z"},"content_sha256":"0516525cfa1162943f364fa48b790c2417affe19c75eeb965a1eeb8deef8a154","schema_version":"1.0","event_id":"sha256:0516525cfa1162943f364fa48b790c2417affe19c75eeb965a1eeb8deef8a154"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VYX65YAHD43PDMFXKTZMZHGYDM/bundle.json","state_url":"https://pith.science/pith/VYX65YAHD43PDMFXKTZMZHGYDM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VYX65YAHD43PDMFXKTZMZHGYDM/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":"2026-05-31T08:16:38Z","links":{"resolver":"https://pith.science/pith/VYX65YAHD43PDMFXKTZMZHGYDM","bundle":"https://pith.science/pith/VYX65YAHD43PDMFXKTZMZHGYDM/bundle.json","state":"https://pith.science/pith/VYX65YAHD43PDMFXKTZMZHGYDM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VYX65YAHD43PDMFXKTZMZHGYDM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VYX65YAHD43PDMFXKTZMZHGYDM","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":"1b18dd16bbf1d40483ae1ff8ba719715cdd58811031e1650f9ada42aef622b4a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T17:25:29Z","title_canon_sha256":"962422f3e77486c6d335fbec4f25a89edfe91cc5da38bc040477c1987a5445ee"},"schema_version":"1.0","source":{"id":"1905.13728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13728","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13728v1","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13728","created_at":"2026-05-17T23:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"VYX65YAHD43P","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VYX65YAHD43PDMFX","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VYX65YAH","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:0516525cfa1162943f364fa48b790c2417affe19c75eeb965a1eeb8deef8a154","target":"graph","created_at":"2026-05-17T23:44:34Z","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":"Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible for some applications. To tackle this problem, we propose a pre-training framework that captures generic graph structural information that is transferable across tasks. Our framework can leverage the following three tasks: 1) denoising link reconstruction, 2) centrality score ranking, and 3) cluster preserving. The pre-training procedure can be conducted pu","authors_text":"Changjun Fan, Kai-Wei Chang, Ting Chen, Yizhou Sun, Ziniu Hu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T17:25:29Z","title":"Pre-Training Graph Neural Networks for Generic Structural Feature Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13728","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":"sha256:3ff8889be43891deae0ea5b6ec45631627ffcce2d653d79fe03a8c07363697dd","target":"record","created_at":"2026-05-17T23:44:34Z","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":"1b18dd16bbf1d40483ae1ff8ba719715cdd58811031e1650f9ada42aef622b4a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T17:25:29Z","title_canon_sha256":"962422f3e77486c6d335fbec4f25a89edfe91cc5da38bc040477c1987a5445ee"},"schema_version":"1.0","source":{"id":"1905.13728","kind":"arxiv","version":1}},"canonical_sha256":"ae2feee0071f36f1b0b754f2cc9cd81b08657cb9990a800b67c02a6271a819ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae2feee0071f36f1b0b754f2cc9cd81b08657cb9990a800b67c02a6271a819ad","first_computed_at":"2026-05-17T23:44:34.098509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:34.098509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EsUdF2uPL0a1bKvG/hzG9fq4nfSM0qpiv7IaHtTCv6aDJs3otf68OV3xfwtGzWsmLDNBw3Htze53UwwD88T9DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:34.099071Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.13728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ff8889be43891deae0ea5b6ec45631627ffcce2d653d79fe03a8c07363697dd","sha256:0516525cfa1162943f364fa48b790c2417affe19c75eeb965a1eeb8deef8a154"],"state_sha256":"3eefb5507fc30cbf98080c988d860103e0d131941d18f004e1303c4386f2c4cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bnAA3/ZeE2G+ul8HI2ZJ5ruJLlTgUUGrrxLpxzwb1TZ6jaRWUEd5v74cB7AjazXZQAAk13dMOzyFSZ+AHLHvAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T08:16:38.892326Z","bundle_sha256":"3cb353b76227f5f97c4b41a57dfda19e1aeeba083b41e39cb0211da8274db1e6"}}