{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DTEV2NOWEXEO4KCSCKV6TNFMI4","short_pith_number":"pith:DTEV2NOW","schema_version":"1.0","canonical_sha256":"1cc95d35d625c8ee285212abe9b4ac47387c47b0e89c3cc1c83068f9d13a4eee","source":{"kind":"arxiv","id":"2309.09455","version":2},"attestation_state":"computed","paper":{"title":"CaT: Balanced Continual Graph Learning with Graph Condensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ruihong Qiu, Yilun Liu, Zi Huang","submitted_at":"2023-09-18T03:28:49Z","abstract_excerpt":"Continual graph learning (CGL) is purposed to continuously update a graph model with graph data being fed in a streaming manner. Since the model easily forgets previously learned knowledge when training with new-coming data, the catastrophic forgetting problem has been the major focus in CGL. Recent replay-based methods intend to solve this problem by updating the model using both (1) the entire new-coming data and (2) a sampling-based memory bank that stores replayed graphs to approximate the distribution of historical data. After updating the model, a new replayed graph sampled from the inco"},"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":"2309.09455","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-18T03:28:49Z","cross_cats_sorted":[],"title_canon_sha256":"deb55005d6f0e4e11c89c983cabcefc7c54c16679140e4748947d1aff90aece1","abstract_canon_sha256":"7054db633092dd7916b669dd5f846c37e1d4179bb14775fa79824c3455ee409d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:49.198153Z","signature_b64":"FE7rKiDJL5BwPXWr6yD0eu4b6STKnaVuwFzpGVYj//c1wJ9fjUYIw3HLySd6d7If9xkDvuUkfheLWR48TSZuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cc95d35d625c8ee285212abe9b4ac47387c47b0e89c3cc1c83068f9d13a4eee","last_reissued_at":"2026-07-05T06:51:49.197685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:49.197685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CaT: Balanced Continual Graph Learning with Graph Condensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ruihong Qiu, Yilun Liu, Zi Huang","submitted_at":"2023-09-18T03:28:49Z","abstract_excerpt":"Continual graph learning (CGL) is purposed to continuously update a graph model with graph data being fed in a streaming manner. Since the model easily forgets previously learned knowledge when training with new-coming data, the catastrophic forgetting problem has been the major focus in CGL. Recent replay-based methods intend to solve this problem by updating the model using both (1) the entire new-coming data and (2) a sampling-based memory bank that stores replayed graphs to approximate the distribution of historical data. After updating the model, a new replayed graph sampled from the inco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09455","kind":"arxiv","version":2},"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/2309.09455/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":"2309.09455","created_at":"2026-07-05T06:51:49.197743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09455v2","created_at":"2026-07-05T06:51:49.197743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09455","created_at":"2026-07-05T06:51:49.197743+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTEV2NOWEXEO","created_at":"2026-07-05T06:51:49.197743+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTEV2NOWEXEO4KCS","created_at":"2026-07-05T06:51:49.197743+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTEV2NOW","created_at":"2026-07-05T06:51:49.197743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00735","citing_title":"Task-Aware Adaptive Modulation: A Replay-Free and Resource-Efficient Approach For Continual Graph Learning","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DTEV2NOWEXEO4KCSCKV6TNFMI4","json":"https://pith.science/pith/DTEV2NOWEXEO4KCSCKV6TNFMI4.json","graph_json":"https://pith.science/api/pith-number/DTEV2NOWEXEO4KCSCKV6TNFMI4/graph.json","events_json":"https://pith.science/api/pith-number/DTEV2NOWEXEO4KCSCKV6TNFMI4/events.json","paper":"https://pith.science/paper/DTEV2NOW"},"agent_actions":{"view_html":"https://pith.science/pith/DTEV2NOWEXEO4KCSCKV6TNFMI4","download_json":"https://pith.science/pith/DTEV2NOWEXEO4KCSCKV6TNFMI4.json","view_paper":"https://pith.science/paper/DTEV2NOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09455&json=true","fetch_graph":"https://pith.science/api/pith-number/DTEV2NOWEXEO4KCSCKV6TNFMI4/graph.json","fetch_events":"https://pith.science/api/pith-number/DTEV2NOWEXEO4KCSCKV6TNFMI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTEV2NOWEXEO4KCSCKV6TNFMI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTEV2NOWEXEO4KCSCKV6TNFMI4/action/storage_attestation","attest_author":"https://pith.science/pith/DTEV2NOWEXEO4KCSCKV6TNFMI4/action/author_attestation","sign_citation":"https://pith.science/pith/DTEV2NOWEXEO4KCSCKV6TNFMI4/action/citation_signature","submit_replication":"https://pith.science/pith/DTEV2NOWEXEO4KCSCKV6TNFMI4/action/replication_record"}},"created_at":"2026-07-05T06:51:49.197743+00:00","updated_at":"2026-07-05T06:51:49.197743+00:00"}