{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MKQHHFBPVLSQDAEXFHIRMKTI7A","short_pith_number":"pith:MKQHHFBP","schema_version":"1.0","canonical_sha256":"62a073942faae501809729d1162a68f836bf7d801344a08a856e755b346aaecd","source":{"kind":"arxiv","id":"2605.20879","version":1},"attestation_state":"computed","paper":{"title":"NeighborDiv: Training-free Zero-shot Generalist Graph Anomaly Detection via Neighbor Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaifeng Wei, Liang Dong, Teng Liu, Xiubo Liang, Yuke Li","submitted_at":"2026-05-20T08:16:13Z","abstract_excerpt":"Graph Anomaly Detection (GAD) is increasingly shifting to Generalist GAD (GGAD) for cross-domain \"one-for-all\" detection, but existing GGAD methods predominantly rely on the neighbor consistency principle, falling into the \\textbf{Node-to-Neighbor Consistency Paradigm} for anomaly quantification. These methods suffer from complex training pipelines, heavy training data dependency, high computational costs, and unstable cross-domain generalization. To address these limitations, we propose NeighborDiv, a training-free generalist graph anomaly detection framework based on neighbor diversity. Depa"},"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":"2605.20879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T08:16:13Z","cross_cats_sorted":[],"title_canon_sha256":"89fed998616abbaae59d1322763e4d5bd7a1aaaa8f7662c885fb773994f3db8e","abstract_canon_sha256":"b43af521c826937aed556edaddaaea57662ae83e4a144b69fd32216cca356de7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:26.090235Z","signature_b64":"PIBEh8EO7YSUUhKSQSw8TmIbF/+s1W4SYGiRSMGVOpLdkFqIB1L6TIFCVwvzK69XQFYGSKZnjmBBHPZ1mT0QCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62a073942faae501809729d1162a68f836bf7d801344a08a856e755b346aaecd","last_reissued_at":"2026-05-21T01:05:26.089466Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:26.089466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeighborDiv: Training-free Zero-shot Generalist Graph Anomaly Detection via Neighbor Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaifeng Wei, Liang Dong, Teng Liu, Xiubo Liang, Yuke Li","submitted_at":"2026-05-20T08:16:13Z","abstract_excerpt":"Graph Anomaly Detection (GAD) is increasingly shifting to Generalist GAD (GGAD) for cross-domain \"one-for-all\" detection, but existing GGAD methods predominantly rely on the neighbor consistency principle, falling into the \\textbf{Node-to-Neighbor Consistency Paradigm} for anomaly quantification. These methods suffer from complex training pipelines, heavy training data dependency, high computational costs, and unstable cross-domain generalization. To address these limitations, we propose NeighborDiv, a training-free generalist graph anomaly detection framework based on neighbor diversity. Depa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20879","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/2605.20879/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":"2605.20879","created_at":"2026-05-21T01:05:26.089602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20879v1","created_at":"2026-05-21T01:05:26.089602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20879","created_at":"2026-05-21T01:05:26.089602+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKQHHFBPVLSQ","created_at":"2026-05-21T01:05:26.089602+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKQHHFBPVLSQDAEX","created_at":"2026-05-21T01:05:26.089602+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKQHHFBP","created_at":"2026-05-21T01:05:26.089602+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/MKQHHFBPVLSQDAEXFHIRMKTI7A","json":"https://pith.science/pith/MKQHHFBPVLSQDAEXFHIRMKTI7A.json","graph_json":"https://pith.science/api/pith-number/MKQHHFBPVLSQDAEXFHIRMKTI7A/graph.json","events_json":"https://pith.science/api/pith-number/MKQHHFBPVLSQDAEXFHIRMKTI7A/events.json","paper":"https://pith.science/paper/MKQHHFBP"},"agent_actions":{"view_html":"https://pith.science/pith/MKQHHFBPVLSQDAEXFHIRMKTI7A","download_json":"https://pith.science/pith/MKQHHFBPVLSQDAEXFHIRMKTI7A.json","view_paper":"https://pith.science/paper/MKQHHFBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20879&json=true","fetch_graph":"https://pith.science/api/pith-number/MKQHHFBPVLSQDAEXFHIRMKTI7A/graph.json","fetch_events":"https://pith.science/api/pith-number/MKQHHFBPVLSQDAEXFHIRMKTI7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKQHHFBPVLSQDAEXFHIRMKTI7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKQHHFBPVLSQDAEXFHIRMKTI7A/action/storage_attestation","attest_author":"https://pith.science/pith/MKQHHFBPVLSQDAEXFHIRMKTI7A/action/author_attestation","sign_citation":"https://pith.science/pith/MKQHHFBPVLSQDAEXFHIRMKTI7A/action/citation_signature","submit_replication":"https://pith.science/pith/MKQHHFBPVLSQDAEXFHIRMKTI7A/action/replication_record"}},"created_at":"2026-05-21T01:05:26.089602+00:00","updated_at":"2026-05-21T01:05:26.089602+00:00"}