{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:732FPYTF74RVGACM737JVK5RFK","short_pith_number":"pith:732FPYTF","schema_version":"1.0","canonical_sha256":"fef457e265ff2353004cfefe9aabb12a9a75cedab60fdd0242e57b0090ad9b51","source":{"kind":"arxiv","id":"2410.14886","version":2},"attestation_state":"computed","paper":{"title":"Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Prompts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changlu Chen, Chaoxi Niu, Guansong Pang, Hezhe Qiao, Ling Chen","submitted_at":"2024-10-18T22:23:59Z","abstract_excerpt":"Graph anomaly detection (GAD), which aims to identify nodes in a graph that significantly deviate from normal patterns, plays a crucial role in broad application domains. However, existing GAD methods are one-model-for-one-dataset approaches, i.e., training a separate model for each graph dataset. This largely limits their applicability in real-world scenarios. To overcome this limitation, we propose a novel zero-shot generalist GAD approach UNPrompt that trains a one-for-all detection model, requiring the training of one GAD model on a single graph dataset and then effectively generalizing to"},"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":"2410.14886","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T22:23:59Z","cross_cats_sorted":[],"title_canon_sha256":"44c1e1df7dbd98d550bb63e0d2187420ffe9920e64003596fba696429020e05f","abstract_canon_sha256":"31f510a267208262c62b4297e6e343bdb8fd3514a33f2743f690d3ff22f82b8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:36.574183Z","signature_b64":"habUiMXDrZ/UXxEFrnzXehrIJc3cnFdZ6tObV7OY9a+kqD1o154AO9X3MZf6L1CAbei8uMeRGSInR+8ksyl7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fef457e265ff2353004cfefe9aabb12a9a75cedab60fdd0242e57b0090ad9b51","last_reissued_at":"2026-07-05T11:17:36.573629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:36.573629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Prompts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changlu Chen, Chaoxi Niu, Guansong Pang, Hezhe Qiao, Ling Chen","submitted_at":"2024-10-18T22:23:59Z","abstract_excerpt":"Graph anomaly detection (GAD), which aims to identify nodes in a graph that significantly deviate from normal patterns, plays a crucial role in broad application domains. However, existing GAD methods are one-model-for-one-dataset approaches, i.e., training a separate model for each graph dataset. This largely limits their applicability in real-world scenarios. To overcome this limitation, we propose a novel zero-shot generalist GAD approach UNPrompt that trains a one-for-all detection model, requiring the training of one GAD model on a single graph dataset and then effectively generalizing to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14886","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/2410.14886/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":"2410.14886","created_at":"2026-07-05T11:17:36.573691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14886v2","created_at":"2026-07-05T11:17:36.573691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14886","created_at":"2026-07-05T11:17:36.573691+00:00"},{"alias_kind":"pith_short_12","alias_value":"732FPYTF74RV","created_at":"2026-07-05T11:17:36.573691+00:00"},{"alias_kind":"pith_short_16","alias_value":"732FPYTF74RVGACM","created_at":"2026-07-05T11:17:36.573691+00:00"},{"alias_kind":"pith_short_8","alias_value":"732FPYTF","created_at":"2026-07-05T11:17:36.573691+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22914","citing_title":"PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30009","citing_title":"Node-to-Neighborhood Semantic Consistency: Text-Topology Alignment for TAGs Anomaly Detection","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25429","citing_title":"Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29526","citing_title":"Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20879","citing_title":"NeighborDiv: Training-free Zero-shot Generalist Graph Anomaly Detection via Neighbor Diversity","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10242","citing_title":"When Normality Shifts: Risk-Aware Test-Time Adaptation for Unsupervised Tabular Anomaly Detection","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/732FPYTF74RVGACM737JVK5RFK","json":"https://pith.science/pith/732FPYTF74RVGACM737JVK5RFK.json","graph_json":"https://pith.science/api/pith-number/732FPYTF74RVGACM737JVK5RFK/graph.json","events_json":"https://pith.science/api/pith-number/732FPYTF74RVGACM737JVK5RFK/events.json","paper":"https://pith.science/paper/732FPYTF"},"agent_actions":{"view_html":"https://pith.science/pith/732FPYTF74RVGACM737JVK5RFK","download_json":"https://pith.science/pith/732FPYTF74RVGACM737JVK5RFK.json","view_paper":"https://pith.science/paper/732FPYTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14886&json=true","fetch_graph":"https://pith.science/api/pith-number/732FPYTF74RVGACM737JVK5RFK/graph.json","fetch_events":"https://pith.science/api/pith-number/732FPYTF74RVGACM737JVK5RFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/732FPYTF74RVGACM737JVK5RFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/732FPYTF74RVGACM737JVK5RFK/action/storage_attestation","attest_author":"https://pith.science/pith/732FPYTF74RVGACM737JVK5RFK/action/author_attestation","sign_citation":"https://pith.science/pith/732FPYTF74RVGACM737JVK5RFK/action/citation_signature","submit_replication":"https://pith.science/pith/732FPYTF74RVGACM737JVK5RFK/action/replication_record"}},"created_at":"2026-07-05T11:17:36.573691+00:00","updated_at":"2026-07-05T11:17:36.573691+00:00"}