{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W2A3Z6LKL5H3MBHZWJIOCQHZ4S","short_pith_number":"pith:W2A3Z6LK","schema_version":"1.0","canonical_sha256":"b681bcf96a5f4fb604f9b250e140f9e4bcb561042b6e0e94c1f3563bf148cd72","source":{"kind":"arxiv","id":"2310.10237","version":2},"attestation_state":"computed","paper":{"title":"SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiannong Cao, Jieming Shi, Shiqi Shen, Xuequn Shang, Zhi Gong, Zhihao Ding, Zhipeng Wang","submitted_at":"2023-10-16T09:51:24Z","abstract_excerpt":"Graph-level representation learning is important in a wide range of applications. Existing graph-level models are generally built on i.i.d. assumption for both training and testing graphs. However, in an open world, models can encounter out-of-distribution (OOD) testing graphs that are from different distributions unknown during training. A trustworthy model should be able to detect OOD graphs to avoid unreliable predictions, while producing accurate in-distribution (ID) predictions. To achieve this, we present SGOOD, a novel graph-level OOD detection framework. We find that substructure diffe"},"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":"2310.10237","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T09:51:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"06b51c87f139a0cd4f790bf74c446a70b2e937f9b0950be026761dfeba2782b6","abstract_canon_sha256":"d3107caa679fd18e967acf08eebef855f9221eccd77a28cb6b9bf2d6a77420ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:22.857523Z","signature_b64":"1elcu/jCC1WBbXDqI3BW2P2PgCpq8vSxA2YH4Xk6ddQsj7N7nLskvBpgWbVl3PSqz0qDruUoapfCWtOZYKcEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b681bcf96a5f4fb604f9b250e140f9e4bcb561042b6e0e94c1f3563bf148cd72","last_reissued_at":"2026-07-05T08:45:22.857036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:22.857036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiannong Cao, Jieming Shi, Shiqi Shen, Xuequn Shang, Zhi Gong, Zhihao Ding, Zhipeng Wang","submitted_at":"2023-10-16T09:51:24Z","abstract_excerpt":"Graph-level representation learning is important in a wide range of applications. Existing graph-level models are generally built on i.i.d. assumption for both training and testing graphs. However, in an open world, models can encounter out-of-distribution (OOD) testing graphs that are from different distributions unknown during training. A trustworthy model should be able to detect OOD graphs to avoid unreliable predictions, while producing accurate in-distribution (ID) predictions. To achieve this, we present SGOOD, a novel graph-level OOD detection framework. We find that substructure diffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10237","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/2310.10237/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":"2310.10237","created_at":"2026-07-05T08:45:22.857093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10237v2","created_at":"2026-07-05T08:45:22.857093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10237","created_at":"2026-07-05T08:45:22.857093+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2A3Z6LKL5H3","created_at":"2026-07-05T08:45:22.857093+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2A3Z6LKL5H3MBHZ","created_at":"2026-07-05T08:45:22.857093+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2A3Z6LK","created_at":"2026-07-05T08:45:22.857093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13429","citing_title":"Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2A3Z6LKL5H3MBHZWJIOCQHZ4S","json":"https://pith.science/pith/W2A3Z6LKL5H3MBHZWJIOCQHZ4S.json","graph_json":"https://pith.science/api/pith-number/W2A3Z6LKL5H3MBHZWJIOCQHZ4S/graph.json","events_json":"https://pith.science/api/pith-number/W2A3Z6LKL5H3MBHZWJIOCQHZ4S/events.json","paper":"https://pith.science/paper/W2A3Z6LK"},"agent_actions":{"view_html":"https://pith.science/pith/W2A3Z6LKL5H3MBHZWJIOCQHZ4S","download_json":"https://pith.science/pith/W2A3Z6LKL5H3MBHZWJIOCQHZ4S.json","view_paper":"https://pith.science/paper/W2A3Z6LK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10237&json=true","fetch_graph":"https://pith.science/api/pith-number/W2A3Z6LKL5H3MBHZWJIOCQHZ4S/graph.json","fetch_events":"https://pith.science/api/pith-number/W2A3Z6LKL5H3MBHZWJIOCQHZ4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2A3Z6LKL5H3MBHZWJIOCQHZ4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2A3Z6LKL5H3MBHZWJIOCQHZ4S/action/storage_attestation","attest_author":"https://pith.science/pith/W2A3Z6LKL5H3MBHZWJIOCQHZ4S/action/author_attestation","sign_citation":"https://pith.science/pith/W2A3Z6LKL5H3MBHZWJIOCQHZ4S/action/citation_signature","submit_replication":"https://pith.science/pith/W2A3Z6LKL5H3MBHZWJIOCQHZ4S/action/replication_record"}},"created_at":"2026-07-05T08:45:22.857093+00:00","updated_at":"2026-07-05T08:45:22.857093+00:00"}