{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SGBJMOOBEFCY7D5E63FGTVW5KH","short_pith_number":"pith:SGBJMOOB","schema_version":"1.0","canonical_sha256":"91829639c121458f8fa4f6ca69d6dd51c4402ace74a242833a804b6c84848932","source":{"kind":"arxiv","id":"2010.16091","version":2},"attestation_state":"computed","paper":{"title":"When Contrastive Learning Meets Active Learning: A Novel Graph Active Learning Paradigm with Self-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Qiang Liu, Shu Wu, Weizhi Xu, Yanqiao Zhu","submitted_at":"2020-10-30T06:20:07Z","abstract_excerpt":"This paper studies active learning (AL) on graphs, whose purpose is to discover the most informative nodes to maximize the performance of graph neural networks (GNNs). Previously, most graph AL methods focus on learning node representations from a carefully selected labeled dataset with large amount of unlabeled data neglected. Motivated by the success of contrastive learning (CL), we propose a novel paradigm that seamlessly integrates graph AL with CL. While being able to leverage the power of abundant unlabeled data in a self-supervised manner, nodes selected by AL further provide semantic i"},"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":"2010.16091","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-30T06:20:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fe4eed761c6eca826dc3902d378ccea71da93fa1de3d06aa902b92583c51515b","abstract_canon_sha256":"31faec446821a5d5c9ea0b519cdf22f2bf8b3ad7ed3950bcf1624ce48d966b44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:34.066493Z","signature_b64":"AGfHjmHzMkwywnOQe93dQcfp+fXJhVR3nHVK1iT3a8MkhJFaGUyFrgfkfZ/KCUNIq4swp50S+3ZnHs8tAKulBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91829639c121458f8fa4f6ca69d6dd51c4402ace74a242833a804b6c84848932","last_reissued_at":"2026-07-05T02:32:34.065962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:34.065962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Contrastive Learning Meets Active Learning: A Novel Graph Active Learning Paradigm with Self-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Qiang Liu, Shu Wu, Weizhi Xu, Yanqiao Zhu","submitted_at":"2020-10-30T06:20:07Z","abstract_excerpt":"This paper studies active learning (AL) on graphs, whose purpose is to discover the most informative nodes to maximize the performance of graph neural networks (GNNs). Previously, most graph AL methods focus on learning node representations from a carefully selected labeled dataset with large amount of unlabeled data neglected. Motivated by the success of contrastive learning (CL), we propose a novel paradigm that seamlessly integrates graph AL with CL. While being able to leverage the power of abundant unlabeled data in a self-supervised manner, nodes selected by AL further provide semantic i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.16091","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/2010.16091/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":"2010.16091","created_at":"2026-07-05T02:32:34.066026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.16091v2","created_at":"2026-07-05T02:32:34.066026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.16091","created_at":"2026-07-05T02:32:34.066026+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGBJMOOBEFCY","created_at":"2026-07-05T02:32:34.066026+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGBJMOOBEFCY7D5E","created_at":"2026-07-05T02:32:34.066026+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGBJMOOB","created_at":"2026-07-05T02:32:34.066026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15763","citing_title":"Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGBJMOOBEFCY7D5E63FGTVW5KH","json":"https://pith.science/pith/SGBJMOOBEFCY7D5E63FGTVW5KH.json","graph_json":"https://pith.science/api/pith-number/SGBJMOOBEFCY7D5E63FGTVW5KH/graph.json","events_json":"https://pith.science/api/pith-number/SGBJMOOBEFCY7D5E63FGTVW5KH/events.json","paper":"https://pith.science/paper/SGBJMOOB"},"agent_actions":{"view_html":"https://pith.science/pith/SGBJMOOBEFCY7D5E63FGTVW5KH","download_json":"https://pith.science/pith/SGBJMOOBEFCY7D5E63FGTVW5KH.json","view_paper":"https://pith.science/paper/SGBJMOOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.16091&json=true","fetch_graph":"https://pith.science/api/pith-number/SGBJMOOBEFCY7D5E63FGTVW5KH/graph.json","fetch_events":"https://pith.science/api/pith-number/SGBJMOOBEFCY7D5E63FGTVW5KH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGBJMOOBEFCY7D5E63FGTVW5KH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGBJMOOBEFCY7D5E63FGTVW5KH/action/storage_attestation","attest_author":"https://pith.science/pith/SGBJMOOBEFCY7D5E63FGTVW5KH/action/author_attestation","sign_citation":"https://pith.science/pith/SGBJMOOBEFCY7D5E63FGTVW5KH/action/citation_signature","submit_replication":"https://pith.science/pith/SGBJMOOBEFCY7D5E63FGTVW5KH/action/replication_record"}},"created_at":"2026-07-05T02:32:34.066026+00:00","updated_at":"2026-07-05T02:32:34.066026+00:00"}