{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4ZRQRLEWBPZ7AFTF2HAAM6XKMX","short_pith_number":"pith:4ZRQRLEW","schema_version":"1.0","canonical_sha256":"e66308ac960bf3f01665d1c0067aea65ea0964e77747da39fa1a0fd4a3894996","source":{"kind":"arxiv","id":"2201.07986","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Guandong Xu, Hongxu Chen, Sixiao Zhang, Xiangguo Sun, Yicong Li","submitted_at":"2022-01-20T03:32:21Z","abstract_excerpt":"Graph contrastive learning is the state-of-the-art unsupervised graph representation learning framework and has shown comparable performance with supervised approaches. However, evaluating whether the graph contrastive learning is robust to adversarial attacks is still an open problem because most existing graph adversarial attacks are supervised models, which means they heavily rely on labels and can only be used to evaluate the graph contrastive learning in a specific scenario. For unsupervised graph representation methods such as graph contrastive learning, it is difficult to acquire labels"},"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":"2201.07986","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-20T03:32:21Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"11e1d7e0e60d7a2c883f2463df3e3f23d25bdaf2dd514c59dfcad63658bcc21c","abstract_canon_sha256":"cb4bcd90b58cc98e7bc36dfa8ef57a30e1c67c59388f0227a2379b122d8c30e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:58.467213Z","signature_b64":"TppDB0DmWCRtFITedCTnBfsEQnszgGMrPezZXktKLWgO0ZjLk9GpDqFobmUz+4tUwnCL/sxwWVA1KZYEvrZoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e66308ac960bf3f01665d1c0067aea65ea0964e77747da39fa1a0fd4a3894996","last_reissued_at":"2026-07-05T03:51:58.466765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:58.466765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Guandong Xu, Hongxu Chen, Sixiao Zhang, Xiangguo Sun, Yicong Li","submitted_at":"2022-01-20T03:32:21Z","abstract_excerpt":"Graph contrastive learning is the state-of-the-art unsupervised graph representation learning framework and has shown comparable performance with supervised approaches. However, evaluating whether the graph contrastive learning is robust to adversarial attacks is still an open problem because most existing graph adversarial attacks are supervised models, which means they heavily rely on labels and can only be used to evaluate the graph contrastive learning in a specific scenario. For unsupervised graph representation methods such as graph contrastive learning, it is difficult to acquire labels"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.07986","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/2201.07986/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":"2201.07986","created_at":"2026-07-05T03:51:58.466835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.07986v3","created_at":"2026-07-05T03:51:58.466835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.07986","created_at":"2026-07-05T03:51:58.466835+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZRQRLEWBPZ7","created_at":"2026-07-05T03:51:58.466835+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZRQRLEWBPZ7AFTF","created_at":"2026-07-05T03:51:58.466835+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZRQRLEW","created_at":"2026-07-05T03:51:58.466835+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/4ZRQRLEWBPZ7AFTF2HAAM6XKMX","json":"https://pith.science/pith/4ZRQRLEWBPZ7AFTF2HAAM6XKMX.json","graph_json":"https://pith.science/api/pith-number/4ZRQRLEWBPZ7AFTF2HAAM6XKMX/graph.json","events_json":"https://pith.science/api/pith-number/4ZRQRLEWBPZ7AFTF2HAAM6XKMX/events.json","paper":"https://pith.science/paper/4ZRQRLEW"},"agent_actions":{"view_html":"https://pith.science/pith/4ZRQRLEWBPZ7AFTF2HAAM6XKMX","download_json":"https://pith.science/pith/4ZRQRLEWBPZ7AFTF2HAAM6XKMX.json","view_paper":"https://pith.science/paper/4ZRQRLEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.07986&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZRQRLEWBPZ7AFTF2HAAM6XKMX/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZRQRLEWBPZ7AFTF2HAAM6XKMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZRQRLEWBPZ7AFTF2HAAM6XKMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZRQRLEWBPZ7AFTF2HAAM6XKMX/action/storage_attestation","attest_author":"https://pith.science/pith/4ZRQRLEWBPZ7AFTF2HAAM6XKMX/action/author_attestation","sign_citation":"https://pith.science/pith/4ZRQRLEWBPZ7AFTF2HAAM6XKMX/action/citation_signature","submit_replication":"https://pith.science/pith/4ZRQRLEWBPZ7AFTF2HAAM6XKMX/action/replication_record"}},"created_at":"2026-07-05T03:51:58.466835+00:00","updated_at":"2026-07-05T03:51:58.466835+00:00"}