{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WGNTUK552MD7POWYVGT6G5ZF43","short_pith_number":"pith:WGNTUK55","schema_version":"1.0","canonical_sha256":"b19b3a2bbdd307f7bad8a9a7e37725e6ef03bed9526893fbb0efa02b4dc040da","source":{"kind":"arxiv","id":"2002.07962","version":1},"attestation_state":"computed","paper":{"title":"Inductive Representation Learning on Temporal Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuanwei Ruan, Da Xu, Evren Korpeoglu, Kannan Achan, Sushant Kumar","submitted_at":"2020-02-19T02:05:37Z","abstract_excerpt":"Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the static node features and the evolving topological structures. Moreover, node and topological features can be temporal as well, whose patterns the node embeddings should also capture. We propose the temporal graph attention (TGAT) layer to efficiently aggregate tempor"},"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":"2002.07962","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-19T02:05:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"67ef1bd6be9756ff73638612bfe6635ead871da5e5ecbdbc00068bccf65391a2","abstract_canon_sha256":"3655a9864e51f517a8f216bff1bd96813cac7c174bfc73f8db03035c5bd98ed5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:25.134440Z","signature_b64":"j1lYGiQKA6BCnpK+IEKhTYMufxYtpB69HswLb6KaZDXAChcBr3nRyPrar8PSLPra2+TOWqVr9oBB4r/w1YMXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b19b3a2bbdd307f7bad8a9a7e37725e6ef03bed9526893fbb0efa02b4dc040da","last_reissued_at":"2026-07-05T00:42:25.133936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:25.133936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inductive Representation Learning on Temporal Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuanwei Ruan, Da Xu, Evren Korpeoglu, Kannan Achan, Sushant Kumar","submitted_at":"2020-02-19T02:05:37Z","abstract_excerpt":"Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the static node features and the evolving topological structures. Moreover, node and topological features can be temporal as well, whose patterns the node embeddings should also capture. We propose the temporal graph attention (TGAT) layer to efficiently aggregate tempor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07962","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/2002.07962/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":"2002.07962","created_at":"2026-07-05T00:42:25.134003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.07962v1","created_at":"2026-07-05T00:42:25.134003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07962","created_at":"2026-07-05T00:42:25.134003+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGNTUK552MD7","created_at":"2026-07-05T00:42:25.134003+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGNTUK552MD7POWY","created_at":"2026-07-05T00:42:25.134003+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGNTUK55","created_at":"2026-07-05T00:42:25.134003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12998","citing_title":"DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26290","citing_title":"Dynamic Link Prediction with Temporally Enhanced Signed Graph Neural Networks","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27063","citing_title":"Learning Dynamic Graph Representations through Timespan View Contrasts","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28155","citing_title":"Temporal Hyperbolic Graph Representation Learning for Scale-Free Internet Routing and Delay Prediction","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29453","citing_title":"Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23887","citing_title":"CHRONOS: Temporally-Aware Multi-Agent Coordination for Evolving Data Marketplaces","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2411.11259","citing_title":"Graph Retention Networks for Dynamic Graphs","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21916","citing_title":"A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2508.12674","citing_title":"Unfolded Laplacian Spectral Embedding: A Theoretically Grounded Approach to Dynamic Network Representation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17071","citing_title":"AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12998","citing_title":"DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12998","citing_title":"DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22781","citing_title":"BiTA: Bidirectional Gated Recurrent Unit-Transformer Aggregator in a Temporal Graph Network Framework for Alert Prediction in Computer Networks","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04976","citing_title":"Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08679","citing_title":"Attention-based graph neural networks: a survey","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24811","citing_title":"Time-varying Interaction Graph ODE for Dynamic Graph Representation Learning","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGNTUK552MD7POWYVGT6G5ZF43","json":"https://pith.science/pith/WGNTUK552MD7POWYVGT6G5ZF43.json","graph_json":"https://pith.science/api/pith-number/WGNTUK552MD7POWYVGT6G5ZF43/graph.json","events_json":"https://pith.science/api/pith-number/WGNTUK552MD7POWYVGT6G5ZF43/events.json","paper":"https://pith.science/paper/WGNTUK55"},"agent_actions":{"view_html":"https://pith.science/pith/WGNTUK552MD7POWYVGT6G5ZF43","download_json":"https://pith.science/pith/WGNTUK552MD7POWYVGT6G5ZF43.json","view_paper":"https://pith.science/paper/WGNTUK55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.07962&json=true","fetch_graph":"https://pith.science/api/pith-number/WGNTUK552MD7POWYVGT6G5ZF43/graph.json","fetch_events":"https://pith.science/api/pith-number/WGNTUK552MD7POWYVGT6G5ZF43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGNTUK552MD7POWYVGT6G5ZF43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGNTUK552MD7POWYVGT6G5ZF43/action/storage_attestation","attest_author":"https://pith.science/pith/WGNTUK552MD7POWYVGT6G5ZF43/action/author_attestation","sign_citation":"https://pith.science/pith/WGNTUK552MD7POWYVGT6G5ZF43/action/citation_signature","submit_replication":"https://pith.science/pith/WGNTUK552MD7POWYVGT6G5ZF43/action/replication_record"}},"created_at":"2026-07-05T00:42:25.134003+00:00","updated_at":"2026-07-05T00:42:25.134003+00:00"}