{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OZYMZ3LSL2NNMV4TWZOFSQJSMO","short_pith_number":"pith:OZYMZ3LS","canonical_record":{"source":{"id":"2205.05964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-12T09:06:04Z","cross_cats_sorted":[],"title_canon_sha256":"dd88f4292c9229030e8ca57d761ad3e37df0b8a67d455bd748e5bb1a45c745d3","abstract_canon_sha256":"4ed1dcadada0523d0d0f1a7694055a71854cc69483f78470434550a5eceb0667"},"schema_version":"1.0"},"canonical_sha256":"7670cced725e9ad65793b65c59413263b60823635b657e95258f18b72af1fdca","source":{"kind":"arxiv","id":"2205.05964","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05964","created_at":"2026-07-05T04:22:44Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05964v1","created_at":"2026-07-05T04:22:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05964","created_at":"2026-07-05T04:22:44Z"},{"alias_kind":"pith_short_12","alias_value":"OZYMZ3LSL2NN","created_at":"2026-07-05T04:22:44Z"},{"alias_kind":"pith_short_16","alias_value":"OZYMZ3LSL2NNMV4T","created_at":"2026-07-05T04:22:44Z"},{"alias_kind":"pith_short_8","alias_value":"OZYMZ3LS","created_at":"2026-07-05T04:22:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OZYMZ3LSL2NNMV4TWZOFSQJSMO","target":"record","payload":{"canonical_record":{"source":{"id":"2205.05964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-12T09:06:04Z","cross_cats_sorted":[],"title_canon_sha256":"dd88f4292c9229030e8ca57d761ad3e37df0b8a67d455bd748e5bb1a45c745d3","abstract_canon_sha256":"4ed1dcadada0523d0d0f1a7694055a71854cc69483f78470434550a5eceb0667"},"schema_version":"1.0"},"canonical_sha256":"7670cced725e9ad65793b65c59413263b60823635b657e95258f18b72af1fdca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:44.009411Z","signature_b64":"Lqp8zlYsVWSW2C7g9t+nnssvw42cAKVnR1nzYpC1zw8GCIJB1dvXwi/HtL3UL5/4ZLnCbAZ8qDPtbX0uFlQQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7670cced725e9ad65793b65c59413263b60823635b657e95258f18b72af1fdca","last_reissued_at":"2026-07-05T04:22:44.009077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:44.009077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.05964","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":"2026-07-05T04:22:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J3SyHeZ+QTnQJ5hTWJqHViljVhUxQJlmnOMVNe7uRNCXMF+a19UVeJS1FVoo16PtiDchA5jRyMAOW55w5zj7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:39:06.202232Z"},"content_sha256":"20225d7a95716323f2899530499c462bb58360399c46424680cd5f911a38382b","schema_version":"1.0","event_id":"sha256:20225d7a95716323f2899530499c462bb58360399c46424680cd5f911a38382b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OZYMZ3LSL2NNMV4TWZOFSQJSMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GPN: A Joint Structural Learning Framework for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Deheng Ye, Peilin Zhao, Qianggang Ding, Tingyang Xu","submitted_at":"2022-05-12T09:06:04Z","abstract_excerpt":"Graph neural networks (GNNs) have been applied into a variety of graph tasks. Most existing work of GNNs is based on the assumption that the given graph data is optimal, while it is inevitable that there exists missing or incomplete edges in the graph data for training, leading to degraded performance. In this paper, we propose Generative Predictive Network (GPN), a GNN-based joint learning framework that simultaneously learns the graph structure and the downstream task. Specifically, we develop a bilevel optimization framework for this joint learning task, in which the upper optimization (gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05964","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/2205.05964/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":"2026-07-05T04:22:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pejLLelSyCUhnkiGswdKZ66Ak1QqlPpgEvDQ/pHUL/RI1e2VfdQIZ4hSgfr8i5WUywYvB3T52GUYAm4aH0/nBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:39:06.202979Z"},"content_sha256":"74fddcb732850f1550b5627068018ccbc5167aee5d39ea118f12c3df02960f68","schema_version":"1.0","event_id":"sha256:74fddcb732850f1550b5627068018ccbc5167aee5d39ea118f12c3df02960f68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OZYMZ3LSL2NNMV4TWZOFSQJSMO/bundle.json","state_url":"https://pith.science/pith/OZYMZ3LSL2NNMV4TWZOFSQJSMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OZYMZ3LSL2NNMV4TWZOFSQJSMO/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":"2026-07-13T00:39:06Z","links":{"resolver":"https://pith.science/pith/OZYMZ3LSL2NNMV4TWZOFSQJSMO","bundle":"https://pith.science/pith/OZYMZ3LSL2NNMV4TWZOFSQJSMO/bundle.json","state":"https://pith.science/pith/OZYMZ3LSL2NNMV4TWZOFSQJSMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OZYMZ3LSL2NNMV4TWZOFSQJSMO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OZYMZ3LSL2NNMV4TWZOFSQJSMO","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":"4ed1dcadada0523d0d0f1a7694055a71854cc69483f78470434550a5eceb0667","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-12T09:06:04Z","title_canon_sha256":"dd88f4292c9229030e8ca57d761ad3e37df0b8a67d455bd748e5bb1a45c745d3"},"schema_version":"1.0","source":{"id":"2205.05964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05964","created_at":"2026-07-05T04:22:44Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05964v1","created_at":"2026-07-05T04:22:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05964","created_at":"2026-07-05T04:22:44Z"},{"alias_kind":"pith_short_12","alias_value":"OZYMZ3LSL2NN","created_at":"2026-07-05T04:22:44Z"},{"alias_kind":"pith_short_16","alias_value":"OZYMZ3LSL2NNMV4T","created_at":"2026-07-05T04:22:44Z"},{"alias_kind":"pith_short_8","alias_value":"OZYMZ3LS","created_at":"2026-07-05T04:22:44Z"}],"graph_snapshots":[{"event_id":"sha256:74fddcb732850f1550b5627068018ccbc5167aee5d39ea118f12c3df02960f68","target":"graph","created_at":"2026-07-05T04:22:44Z","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/2205.05964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph neural networks (GNNs) have been applied into a variety of graph tasks. Most existing work of GNNs is based on the assumption that the given graph data is optimal, while it is inevitable that there exists missing or incomplete edges in the graph data for training, leading to degraded performance. In this paper, we propose Generative Predictive Network (GPN), a GNN-based joint learning framework that simultaneously learns the graph structure and the downstream task. Specifically, we develop a bilevel optimization framework for this joint learning task, in which the upper optimization (gen","authors_text":"Deheng Ye, Peilin Zhao, Qianggang Ding, Tingyang Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-12T09:06:04Z","title":"GPN: A Joint Structural Learning Framework for Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05964","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":"sha256:20225d7a95716323f2899530499c462bb58360399c46424680cd5f911a38382b","target":"record","created_at":"2026-07-05T04:22:44Z","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":"4ed1dcadada0523d0d0f1a7694055a71854cc69483f78470434550a5eceb0667","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-12T09:06:04Z","title_canon_sha256":"dd88f4292c9229030e8ca57d761ad3e37df0b8a67d455bd748e5bb1a45c745d3"},"schema_version":"1.0","source":{"id":"2205.05964","kind":"arxiv","version":1}},"canonical_sha256":"7670cced725e9ad65793b65c59413263b60823635b657e95258f18b72af1fdca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7670cced725e9ad65793b65c59413263b60823635b657e95258f18b72af1fdca","first_computed_at":"2026-07-05T04:22:44.009077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:44.009077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lqp8zlYsVWSW2C7g9t+nnssvw42cAKVnR1nzYpC1zw8GCIJB1dvXwi/HtL3UL5/4ZLnCbAZ8qDPtbX0uFlQQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:44.009411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.05964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20225d7a95716323f2899530499c462bb58360399c46424680cd5f911a38382b","sha256:74fddcb732850f1550b5627068018ccbc5167aee5d39ea118f12c3df02960f68"],"state_sha256":"906fb5d8b1563bdb5249fae5f611511b4d2752a94227bd8b945872b787c90585"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qS2Dg5/SQa2vseSow330LY3YrNcMu3odGOrijOYQgrMhNRIrLn/iJuQBozzjsLwHGiPLnLHbg4C5/dmeoHDkDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T00:39:06.206887Z","bundle_sha256":"6fb27ba728cc1fa6caa0f0259e4573bf1b7e192b0ebb3b4c551f27f65402342b"}}