{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ELWQYEZ2CKWUXGCDHHSALQCHCI","short_pith_number":"pith:ELWQYEZ2","schema_version":"1.0","canonical_sha256":"22ed0c133a12ad4b984339e405c047123805f0c55af34ea04a756e2f095ce616","source":{"kind":"arxiv","id":"2012.06002","version":1},"attestation_state":"computed","paper":{"title":"Overcoming Catastrophic Forgetting in Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huihui Liu, Xinchao Wang, Yiding Yang","submitted_at":"2020-12-10T22:30:25Z","abstract_excerpt":"Catastrophic forgetting refers to the tendency that a neural network \"forgets\" the previous learned knowledge upon learning new tasks. Prior methods have been focused on overcoming this problem on convolutional neural networks (CNNs), where the input samples like images lie in a grid domain, but have largely overlooked graph neural networks (GNNs) that handle non-grid data. In this paper, we propose a novel scheme dedicated to overcoming catastrophic forgetting problem and hence strengthen continual learning in GNNs. At the heart of our approach is a generic module, termed as topology-aware we"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2012.06002","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-10T22:30:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d40e5a6e6dd0f9d793c930de3d0b238d22a05ff5c0a2fe6c78c7ef4ea026e471","abstract_canon_sha256":"c784db8db0d3516911cecba37fd72c8dc625b87fd4f98c3115ed9b1a99100642"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:46.043145Z","signature_b64":"TzdrrzyIhto6QpCa6w7UvOMcOQdF/05IsC92D3q8FqjkZP9ItAs1yshNcgrJNWiJBhEQwHCzC5C1Q0NFZRUrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22ed0c133a12ad4b984339e405c047123805f0c55af34ea04a756e2f095ce616","last_reissued_at":"2026-07-05T01:58:46.042622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:46.042622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Catastrophic Forgetting in Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huihui Liu, Xinchao Wang, Yiding Yang","submitted_at":"2020-12-10T22:30:25Z","abstract_excerpt":"Catastrophic forgetting refers to the tendency that a neural network \"forgets\" the previous learned knowledge upon learning new tasks. Prior methods have been focused on overcoming this problem on convolutional neural networks (CNNs), where the input samples like images lie in a grid domain, but have largely overlooked graph neural networks (GNNs) that handle non-grid data. In this paper, we propose a novel scheme dedicated to overcoming catastrophic forgetting problem and hence strengthen continual learning in GNNs. At the heart of our approach is a generic module, termed as topology-aware we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06002","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/2012.06002/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2012.06002","created_at":"2026-07-05T01:58:46.042686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.06002v1","created_at":"2026-07-05T01:58:46.042686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06002","created_at":"2026-07-05T01:58:46.042686+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELWQYEZ2CKWU","created_at":"2026-07-05T01:58:46.042686+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELWQYEZ2CKWUXGCD","created_at":"2026-07-05T01:58:46.042686+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELWQYEZ2","created_at":"2026-07-05T01:58:46.042686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22429","citing_title":"Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation","ref_index":244,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELWQYEZ2CKWUXGCDHHSALQCHCI","json":"https://pith.science/pith/ELWQYEZ2CKWUXGCDHHSALQCHCI.json","graph_json":"https://pith.science/api/pith-number/ELWQYEZ2CKWUXGCDHHSALQCHCI/graph.json","events_json":"https://pith.science/api/pith-number/ELWQYEZ2CKWUXGCDHHSALQCHCI/events.json","paper":"https://pith.science/paper/ELWQYEZ2"},"agent_actions":{"view_html":"https://pith.science/pith/ELWQYEZ2CKWUXGCDHHSALQCHCI","download_json":"https://pith.science/pith/ELWQYEZ2CKWUXGCDHHSALQCHCI.json","view_paper":"https://pith.science/paper/ELWQYEZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.06002&json=true","fetch_graph":"https://pith.science/api/pith-number/ELWQYEZ2CKWUXGCDHHSALQCHCI/graph.json","fetch_events":"https://pith.science/api/pith-number/ELWQYEZ2CKWUXGCDHHSALQCHCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELWQYEZ2CKWUXGCDHHSALQCHCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELWQYEZ2CKWUXGCDHHSALQCHCI/action/storage_attestation","attest_author":"https://pith.science/pith/ELWQYEZ2CKWUXGCDHHSALQCHCI/action/author_attestation","sign_citation":"https://pith.science/pith/ELWQYEZ2CKWUXGCDHHSALQCHCI/action/citation_signature","submit_replication":"https://pith.science/pith/ELWQYEZ2CKWUXGCDHHSALQCHCI/action/replication_record"}},"created_at":"2026-07-05T01:58:46.042686+00:00","updated_at":"2026-07-05T01:58:46.042686+00:00"}