{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XPQCHOHCF67P3LQRIEX5LUZL3Y","short_pith_number":"pith:XPQCHOHC","schema_version":"1.0","canonical_sha256":"bbe023b8e22fbefdae11412fd5d32bde1be7e8042bc829e7d07614a43f624820","source":{"kind":"arxiv","id":"2010.13902","version":3},"attestation_state":"computed","paper":{"title":"Graph Contrastive Learning with Augmentations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Tianlong Chen, Ting Chen, Yang Shen, Yongduo Sui, Yuning You, Zhangyang Wang","submitted_at":"2020-10-22T20:13:43Z","abstract_excerpt":"Generalizable, transferrable, and robust representation learning on graph-structured data remains a challenge for current graph neural networks (GNNs). Unlike what has been developed for convolutional neural networks (CNNs) for image data, self-supervised learning and pre-training are less explored for GNNs. In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data. We first design four types of graph augmentations to incorporate various priors. We then systematically study the impact of various combinations of graph augm"},"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":"2010.13902","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T20:13:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f88c3b10cffb46a447dda05c6d01c9c6ee9b329b8c2ae3c04d52a524bbbe505f","abstract_canon_sha256":"7d047f9e83992ce0fa98af6493a098aa0933a53d4c0b044a93105ce4e0b4a75a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:52.705121Z","signature_b64":"oR9yLOnMlOqotasizuugQMSY8yo5/KBvb3FhYYEWYOWQzPAA0QRkojb+fw4Yh/q4D60/7t5fQFX3P8JZCszgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbe023b8e22fbefdae11412fd5d32bde1be7e8042bc829e7d07614a43f624820","last_reissued_at":"2026-07-05T02:28:52.704642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:52.704642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Contrastive Learning with Augmentations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Tianlong Chen, Ting Chen, Yang Shen, Yongduo Sui, Yuning You, Zhangyang Wang","submitted_at":"2020-10-22T20:13:43Z","abstract_excerpt":"Generalizable, transferrable, and robust representation learning on graph-structured data remains a challenge for current graph neural networks (GNNs). Unlike what has been developed for convolutional neural networks (CNNs) for image data, self-supervised learning and pre-training are less explored for GNNs. In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data. We first design four types of graph augmentations to incorporate various priors. We then systematically study the impact of various combinations of graph augm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13902","kind":"arxiv","version":3},"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/2010.13902/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":"2010.13902","created_at":"2026-07-05T02:28:52.704700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.13902v3","created_at":"2026-07-05T02:28:52.704700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13902","created_at":"2026-07-05T02:28:52.704700+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPQCHOHCF67P","created_at":"2026-07-05T02:28:52.704700+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPQCHOHCF67P3LQR","created_at":"2026-07-05T02:28:52.704700+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPQCHOHC","created_at":"2026-07-05T02:28:52.704700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20248","citing_title":"Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19916","citing_title":"Fast and Featureless Node Representation Learning with Partial Pairwise Supervision","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPQCHOHCF67P3LQRIEX5LUZL3Y","json":"https://pith.science/pith/XPQCHOHCF67P3LQRIEX5LUZL3Y.json","graph_json":"https://pith.science/api/pith-number/XPQCHOHCF67P3LQRIEX5LUZL3Y/graph.json","events_json":"https://pith.science/api/pith-number/XPQCHOHCF67P3LQRIEX5LUZL3Y/events.json","paper":"https://pith.science/paper/XPQCHOHC"},"agent_actions":{"view_html":"https://pith.science/pith/XPQCHOHCF67P3LQRIEX5LUZL3Y","download_json":"https://pith.science/pith/XPQCHOHCF67P3LQRIEX5LUZL3Y.json","view_paper":"https://pith.science/paper/XPQCHOHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.13902&json=true","fetch_graph":"https://pith.science/api/pith-number/XPQCHOHCF67P3LQRIEX5LUZL3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/XPQCHOHCF67P3LQRIEX5LUZL3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPQCHOHCF67P3LQRIEX5LUZL3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPQCHOHCF67P3LQRIEX5LUZL3Y/action/storage_attestation","attest_author":"https://pith.science/pith/XPQCHOHCF67P3LQRIEX5LUZL3Y/action/author_attestation","sign_citation":"https://pith.science/pith/XPQCHOHCF67P3LQRIEX5LUZL3Y/action/citation_signature","submit_replication":"https://pith.science/pith/XPQCHOHCF67P3LQRIEX5LUZL3Y/action/replication_record"}},"created_at":"2026-07-05T02:28:52.704700+00:00","updated_at":"2026-07-05T02:28:52.704700+00:00"}