{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZSHIFPPGUTPBTBFMEA4TH3LIY6","short_pith_number":"pith:ZSHIFPPG","canonical_record":{"source":{"id":"2308.06714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-13T08:10:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ee06bbfd6b26f06088b36cdda1e683393df301dff7e371360378c19643306b2","abstract_canon_sha256":"82b5bc09b5d6370bab67819dc0647cd641af0b20c899fdf7930ada00f081405a"},"schema_version":"1.0"},"canonical_sha256":"cc8e82bde6a4de1984ac203933ed68c7844ebc5179d190a2b650e358a90229b9","source":{"kind":"arxiv","id":"2308.06714","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.06714","created_at":"2026-07-05T06:40:44Z"},{"alias_kind":"arxiv_version","alias_value":"2308.06714v1","created_at":"2026-07-05T06:40:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06714","created_at":"2026-07-05T06:40:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZSHIFPPGUTPB","created_at":"2026-07-05T06:40:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZSHIFPPGUTPBTBFM","created_at":"2026-07-05T06:40:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZSHIFPPG","created_at":"2026-07-05T06:40:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZSHIFPPGUTPBTBFMEA4TH3LIY6","target":"record","payload":{"canonical_record":{"source":{"id":"2308.06714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-13T08:10:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ee06bbfd6b26f06088b36cdda1e683393df301dff7e371360378c19643306b2","abstract_canon_sha256":"82b5bc09b5d6370bab67819dc0647cd641af0b20c899fdf7930ada00f081405a"},"schema_version":"1.0"},"canonical_sha256":"cc8e82bde6a4de1984ac203933ed68c7844ebc5179d190a2b650e358a90229b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:44.176610Z","signature_b64":"J4bBxKze/kLlAYBxl7zbAHPhW0J06nl44zv8PUziixU4hJ/9Wopdnoj2O4hOmsYx0RIImQIb3eO4J1N2TgiiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc8e82bde6a4de1984ac203933ed68c7844ebc5179d190a2b650e358a90229b9","last_reissued_at":"2026-07-05T06:40:44.176216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:44.176216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.06714","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":"2026-07-05T06:40:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AH9MG1InpjqEbIvnwkKaR4Q3zGRO/3uTu7XI+2ysRsVYCcim5TrviiUfF1GjKVdlZ+zAO6P/oFTmFNg6STkrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T08:04:06.219024Z"},"content_sha256":"588e70b07f75889fcbe34460e7221924adaae927eccec935d3707865afe52a5a","schema_version":"1.0","event_id":"sha256:588e70b07f75889fcbe34460e7221924adaae927eccec935d3707865afe52a5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZSHIFPPGUTPBTBFMEA4TH3LIY6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning on Graphs with Out-of-Distribution Nodes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Yu Song","submitted_at":"2023-08-13T08:10:23Z","abstract_excerpt":"Graph Neural Networks (GNNs) are state-of-the-art models for performing prediction tasks on graphs. While existing GNNs have shown great performance on various tasks related to graphs, little attention has been paid to the scenario where out-of-distribution (OOD) nodes exist in the graph during training and inference. Borrowing the concept from CV and NLP, we define OOD nodes as nodes with labels unseen from the training set. Since a lot of networks are automatically constructed by programs, real-world graphs are often noisy and may contain nodes from unknown distributions. In this work, we de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06714","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/2308.06714/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":"2026-07-05T06:40:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PbHWH6p7w9SmggcSsy+rpETndINbl9C76BLbx6N5UuDeaBONW4sQ4xBWFB22g1g5w0dLGrHB0wUm7ToCfXoBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T08:04:06.219406Z"},"content_sha256":"29373293857eea4c78c4da893cb2c1333b5adb4f536a32f2437510a811f3a6c8","schema_version":"1.0","event_id":"sha256:29373293857eea4c78c4da893cb2c1333b5adb4f536a32f2437510a811f3a6c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSHIFPPGUTPBTBFMEA4TH3LIY6/bundle.json","state_url":"https://pith.science/pith/ZSHIFPPGUTPBTBFMEA4TH3LIY6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSHIFPPGUTPBTBFMEA4TH3LIY6/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":"2026-07-22T08:04:06Z","links":{"resolver":"https://pith.science/pith/ZSHIFPPGUTPBTBFMEA4TH3LIY6","bundle":"https://pith.science/pith/ZSHIFPPGUTPBTBFMEA4TH3LIY6/bundle.json","state":"https://pith.science/pith/ZSHIFPPGUTPBTBFMEA4TH3LIY6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSHIFPPGUTPBTBFMEA4TH3LIY6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZSHIFPPGUTPBTBFMEA4TH3LIY6","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":"82b5bc09b5d6370bab67819dc0647cd641af0b20c899fdf7930ada00f081405a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-13T08:10:23Z","title_canon_sha256":"1ee06bbfd6b26f06088b36cdda1e683393df301dff7e371360378c19643306b2"},"schema_version":"1.0","source":{"id":"2308.06714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.06714","created_at":"2026-07-05T06:40:44Z"},{"alias_kind":"arxiv_version","alias_value":"2308.06714v1","created_at":"2026-07-05T06:40:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06714","created_at":"2026-07-05T06:40:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZSHIFPPGUTPB","created_at":"2026-07-05T06:40:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZSHIFPPGUTPBTBFM","created_at":"2026-07-05T06:40:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZSHIFPPG","created_at":"2026-07-05T06:40:44Z"}],"graph_snapshots":[{"event_id":"sha256:29373293857eea4c78c4da893cb2c1333b5adb4f536a32f2437510a811f3a6c8","target":"graph","created_at":"2026-07-05T06:40:44Z","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/2308.06714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) are state-of-the-art models for performing prediction tasks on graphs. While existing GNNs have shown great performance on various tasks related to graphs, little attention has been paid to the scenario where out-of-distribution (OOD) nodes exist in the graph during training and inference. Borrowing the concept from CV and NLP, we define OOD nodes as nodes with labels unseen from the training set. Since a lot of networks are automatically constructed by programs, real-world graphs are often noisy and may contain nodes from unknown distributions. In this work, we de","authors_text":"Donglin Wang, Yu Song","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-13T08:10:23Z","title":"Learning on Graphs with Out-of-Distribution Nodes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06714","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":"sha256:588e70b07f75889fcbe34460e7221924adaae927eccec935d3707865afe52a5a","target":"record","created_at":"2026-07-05T06:40:44Z","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":"82b5bc09b5d6370bab67819dc0647cd641af0b20c899fdf7930ada00f081405a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-13T08:10:23Z","title_canon_sha256":"1ee06bbfd6b26f06088b36cdda1e683393df301dff7e371360378c19643306b2"},"schema_version":"1.0","source":{"id":"2308.06714","kind":"arxiv","version":1}},"canonical_sha256":"cc8e82bde6a4de1984ac203933ed68c7844ebc5179d190a2b650e358a90229b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc8e82bde6a4de1984ac203933ed68c7844ebc5179d190a2b650e358a90229b9","first_computed_at":"2026-07-05T06:40:44.176216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:40:44.176216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J4bBxKze/kLlAYBxl7zbAHPhW0J06nl44zv8PUziixU4hJ/9Wopdnoj2O4hOmsYx0RIImQIb3eO4J1N2TgiiCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:40:44.176610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.06714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:588e70b07f75889fcbe34460e7221924adaae927eccec935d3707865afe52a5a","sha256:29373293857eea4c78c4da893cb2c1333b5adb4f536a32f2437510a811f3a6c8"],"state_sha256":"27b781492c4de3d2dbdd9dc1737e12c44e8540a2e96e9de9bd435654a59c5eb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"flOGiSzE1ygmwbfwu4xiFbfsBtNOCrB5/JC/uTqdTFKOkdplXb+G3j1MBke8GTNf4UFs5/DcKKWVeCFmhSCeDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T08:04:06.221480Z","bundle_sha256":"b3086480f686b60b21e2b98d222009fcfa2b45d97b4b0186db31a88e2f30c4db"}}