{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6MVTZLUUYJCN6CSXYOYTF5IYAM","short_pith_number":"pith:6MVTZLUU","schema_version":"1.0","canonical_sha256":"f32b3cae94c244df0a57c3b132f51803029939681e78bfd4ada1999c715408c8","source":{"kind":"arxiv","id":"2305.18675","version":1},"attestation_state":"computed","paper":{"title":"History Repeats: Overcoming Catastrophic Forgetting For Event-Centric Temporal Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aram Galstyan, Mehrnoosh Mirtaheri, Mohammad Rostami","submitted_at":"2023-05-30T01:21:36Z","abstract_excerpt":"Temporal knowledge graph (TKG) completion models typically rely on having access to the entire graph during training. However, in real-world scenarios, TKG data is often received incrementally as events unfold, leading to a dynamic non-stationary data distribution over time. While one could incorporate fine-tuning to existing methods to allow them to adapt to evolving TKG data, this can lead to forgetting previously learned patterns. Alternatively, retraining the model with the entire updated TKG can mitigate forgetting but is computationally burdensome. To address these challenges, we propose"},"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":"2305.18675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-30T01:21:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"aa0617c8b5866c64f0c5f8496a5e0c4f4b578d83473460918afed513613daf35","abstract_canon_sha256":"fd29a6d1e9bc7ebe2b68edaefd93de2eafc3f2457c7aa5665aa231b7b213daaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:03.612250Z","signature_b64":"IVVuAmRPXbhPlef1vLyvP+TllYr+wDR9B0M2RkXDfEiCCWEpzNBxla7Js7Y3Ct4WIvKHdOMjFbN0EW4PcOFTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f32b3cae94c244df0a57c3b132f51803029939681e78bfd4ada1999c715408c8","last_reissued_at":"2026-07-05T06:15:03.611826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:03.611826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"History Repeats: Overcoming Catastrophic Forgetting For Event-Centric Temporal Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aram Galstyan, Mehrnoosh Mirtaheri, Mohammad Rostami","submitted_at":"2023-05-30T01:21:36Z","abstract_excerpt":"Temporal knowledge graph (TKG) completion models typically rely on having access to the entire graph during training. However, in real-world scenarios, TKG data is often received incrementally as events unfold, leading to a dynamic non-stationary data distribution over time. While one could incorporate fine-tuning to existing methods to allow them to adapt to evolving TKG data, this can lead to forgetting previously learned patterns. Alternatively, retraining the model with the entire updated TKG can mitigate forgetting but is computationally burdensome. To address these challenges, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18675","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/2305.18675/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":"2305.18675","created_at":"2026-07-05T06:15:03.611880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18675v1","created_at":"2026-07-05T06:15:03.611880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18675","created_at":"2026-07-05T06:15:03.611880+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MVTZLUUYJCN","created_at":"2026-07-05T06:15:03.611880+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MVTZLUUYJCN6CSX","created_at":"2026-07-05T06:15:03.611880+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MVTZLUU","created_at":"2026-07-05T06:15:03.611880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MVTZLUUYJCN6CSXYOYTF5IYAM","json":"https://pith.science/pith/6MVTZLUUYJCN6CSXYOYTF5IYAM.json","graph_json":"https://pith.science/api/pith-number/6MVTZLUUYJCN6CSXYOYTF5IYAM/graph.json","events_json":"https://pith.science/api/pith-number/6MVTZLUUYJCN6CSXYOYTF5IYAM/events.json","paper":"https://pith.science/paper/6MVTZLUU"},"agent_actions":{"view_html":"https://pith.science/pith/6MVTZLUUYJCN6CSXYOYTF5IYAM","download_json":"https://pith.science/pith/6MVTZLUUYJCN6CSXYOYTF5IYAM.json","view_paper":"https://pith.science/paper/6MVTZLUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18675&json=true","fetch_graph":"https://pith.science/api/pith-number/6MVTZLUUYJCN6CSXYOYTF5IYAM/graph.json","fetch_events":"https://pith.science/api/pith-number/6MVTZLUUYJCN6CSXYOYTF5IYAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MVTZLUUYJCN6CSXYOYTF5IYAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MVTZLUUYJCN6CSXYOYTF5IYAM/action/storage_attestation","attest_author":"https://pith.science/pith/6MVTZLUUYJCN6CSXYOYTF5IYAM/action/author_attestation","sign_citation":"https://pith.science/pith/6MVTZLUUYJCN6CSXYOYTF5IYAM/action/citation_signature","submit_replication":"https://pith.science/pith/6MVTZLUUYJCN6CSXYOYTF5IYAM/action/replication_record"}},"created_at":"2026-07-05T06:15:03.611880+00:00","updated_at":"2026-07-05T06:15:03.611880+00:00"}