{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U5I2KILUAUKDSFCOTEREZL6NJ6","short_pith_number":"pith:U5I2KILU","schema_version":"1.0","canonical_sha256":"a751a52174051439144e99224cafcd4f9d4724ea58d638b0c6cb4b32453fffd9","source":{"kind":"arxiv","id":"2410.16386","version":2},"attestation_state":"computed","paper":{"title":"LEGO-Learn: Label-Efficient Graph Open-Set Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Haoyan Xu, Kaize Ding, Kay Liu, Mengyuan Li, Philip S. Yu, Yue Zhao, Zhengtao Yao","submitted_at":"2024-10-21T18:01:11Z","abstract_excerpt":"How can we train graph-based models to recognize unseen classes while keeping labeling costs low? Graph open-set learning (GOL) and out-of-distribution (OOD) detection aim to address this challenge by training models that can accurately classify known, in-distribution (ID) classes while identifying and handling previously unseen classes during inference. It is critical for high-stakes, real-world applications where models frequently encounter unexpected data, including finance, security, and healthcare. However, current GOL methods assume access to many labeled ID samples, which is unrealistic"},"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":"2410.16386","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-21T18:01:11Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"f67daad58f6bbe89b55143bc8514336f78eb81ad63f6e4d320375c32e30a2c6e","abstract_canon_sha256":"47363e3409692c5d75c0edaa1f7ec009995fb8dcc2d6f639c4c54d4c2f6eeddf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:39.743762Z","signature_b64":"bz7TxWdLOdyhVYpRJzE+933Liwzgq4NlsTvpdILJTesaNBBRRtmVH7VxHM7lXkSNlXqIVbXZZDmpgOkX1bxADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a751a52174051439144e99224cafcd4f9d4724ea58d638b0c6cb4b32453fffd9","last_reissued_at":"2026-07-05T11:00:39.743272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:39.743272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEGO-Learn: Label-Efficient Graph Open-Set Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Haoyan Xu, Kaize Ding, Kay Liu, Mengyuan Li, Philip S. Yu, Yue Zhao, Zhengtao Yao","submitted_at":"2024-10-21T18:01:11Z","abstract_excerpt":"How can we train graph-based models to recognize unseen classes while keeping labeling costs low? Graph open-set learning (GOL) and out-of-distribution (OOD) detection aim to address this challenge by training models that can accurately classify known, in-distribution (ID) classes while identifying and handling previously unseen classes during inference. It is critical for high-stakes, real-world applications where models frequently encounter unexpected data, including finance, security, and healthcare. However, current GOL methods assume access to many labeled ID samples, which is unrealistic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16386","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/2410.16386/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":"2410.16386","created_at":"2026-07-05T11:00:39.743334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16386v2","created_at":"2026-07-05T11:00:39.743334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16386","created_at":"2026-07-05T11:00:39.743334+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5I2KILUAUKD","created_at":"2026-07-05T11:00:39.743334+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5I2KILUAUKDSFCO","created_at":"2026-07-05T11:00:39.743334+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5I2KILU","created_at":"2026-07-05T11:00:39.743334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13989","citing_title":"When LLMs meet open-world graph learning: a new perspective for unlabeled data uncertainty","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5I2KILUAUKDSFCOTEREZL6NJ6","json":"https://pith.science/pith/U5I2KILUAUKDSFCOTEREZL6NJ6.json","graph_json":"https://pith.science/api/pith-number/U5I2KILUAUKDSFCOTEREZL6NJ6/graph.json","events_json":"https://pith.science/api/pith-number/U5I2KILUAUKDSFCOTEREZL6NJ6/events.json","paper":"https://pith.science/paper/U5I2KILU"},"agent_actions":{"view_html":"https://pith.science/pith/U5I2KILUAUKDSFCOTEREZL6NJ6","download_json":"https://pith.science/pith/U5I2KILUAUKDSFCOTEREZL6NJ6.json","view_paper":"https://pith.science/paper/U5I2KILU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16386&json=true","fetch_graph":"https://pith.science/api/pith-number/U5I2KILUAUKDSFCOTEREZL6NJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/U5I2KILUAUKDSFCOTEREZL6NJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5I2KILUAUKDSFCOTEREZL6NJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5I2KILUAUKDSFCOTEREZL6NJ6/action/storage_attestation","attest_author":"https://pith.science/pith/U5I2KILUAUKDSFCOTEREZL6NJ6/action/author_attestation","sign_citation":"https://pith.science/pith/U5I2KILUAUKDSFCOTEREZL6NJ6/action/citation_signature","submit_replication":"https://pith.science/pith/U5I2KILUAUKDSFCOTEREZL6NJ6/action/replication_record"}},"created_at":"2026-07-05T11:00:39.743334+00:00","updated_at":"2026-07-05T11:00:39.743334+00:00"}