{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KPZJBARMUBYBOCEQ6N7GFL2SX2","short_pith_number":"pith:KPZJBARM","schema_version":"1.0","canonical_sha256":"53f290822ca070170890f37e62af52bea894ad3037ad570234141f0d9d1b0a7e","source":{"kind":"arxiv","id":"2505.06282","version":1},"attestation_state":"computed","paper":{"title":"InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingbing Xu, Huawei Shen, Xueqi Cheng, Yige Yuan, Zixu Wang","submitted_at":"2025-05-07T05:27:36Z","abstract_excerpt":"As an important graph pre-training method, Graph Contrastive Learning (GCL) continues to play a crucial role in the ongoing surge of research on graph foundation models or LLM as enhancer for graphs. Traditional GCL optimizes InfoNCE by using augmentations to define self-supervised tasks, treating augmented pairs as positive samples and others as negative. However, this leads to semantically similar pairs being classified as negative, causing significant sampling bias and limiting performance. In this paper, we argue that GCL is essentially a Positive-Unlabeled (PU) learning problem, where the"},"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":"2505.06282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T05:27:36Z","cross_cats_sorted":[],"title_canon_sha256":"94c39a20455a41ac5937023ac1722b06bd1b49d65156d13eac3795962feaf715","abstract_canon_sha256":"4baff31ca361a56aebc56c88d1f14ef0efe9d203a277f5694a4407d778348f9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:06.593862Z","signature_b64":"e7lkauGH+0k/U0LN3FRPj30gOavho1U+G0xBZ7HFxvQrGwqEjuZ7nk+UVu5gy3MEkbQDQwm0QCMn/g+Dz9ETCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53f290822ca070170890f37e62af52bea894ad3037ad570234141f0d9d1b0a7e","last_reissued_at":"2026-07-05T11:01:06.593372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:06.593372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingbing Xu, Huawei Shen, Xueqi Cheng, Yige Yuan, Zixu Wang","submitted_at":"2025-05-07T05:27:36Z","abstract_excerpt":"As an important graph pre-training method, Graph Contrastive Learning (GCL) continues to play a crucial role in the ongoing surge of research on graph foundation models or LLM as enhancer for graphs. Traditional GCL optimizes InfoNCE by using augmentations to define self-supervised tasks, treating augmented pairs as positive samples and others as negative. However, this leads to semantically similar pairs being classified as negative, causing significant sampling bias and limiting performance. In this paper, we argue that GCL is essentially a Positive-Unlabeled (PU) learning problem, where the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06282","kind":"arxiv","version":1},"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/2505.06282/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":"2505.06282","created_at":"2026-07-05T11:01:06.593432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06282v1","created_at":"2026-07-05T11:01:06.593432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06282","created_at":"2026-07-05T11:01:06.593432+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPZJBARMUBYB","created_at":"2026-07-05T11:01:06.593432+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPZJBARMUBYBOCEQ","created_at":"2026-07-05T11:01:06.593432+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPZJBARM","created_at":"2026-07-05T11:01:06.593432+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/KPZJBARMUBYBOCEQ6N7GFL2SX2","json":"https://pith.science/pith/KPZJBARMUBYBOCEQ6N7GFL2SX2.json","graph_json":"https://pith.science/api/pith-number/KPZJBARMUBYBOCEQ6N7GFL2SX2/graph.json","events_json":"https://pith.science/api/pith-number/KPZJBARMUBYBOCEQ6N7GFL2SX2/events.json","paper":"https://pith.science/paper/KPZJBARM"},"agent_actions":{"view_html":"https://pith.science/pith/KPZJBARMUBYBOCEQ6N7GFL2SX2","download_json":"https://pith.science/pith/KPZJBARMUBYBOCEQ6N7GFL2SX2.json","view_paper":"https://pith.science/paper/KPZJBARM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06282&json=true","fetch_graph":"https://pith.science/api/pith-number/KPZJBARMUBYBOCEQ6N7GFL2SX2/graph.json","fetch_events":"https://pith.science/api/pith-number/KPZJBARMUBYBOCEQ6N7GFL2SX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPZJBARMUBYBOCEQ6N7GFL2SX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPZJBARMUBYBOCEQ6N7GFL2SX2/action/storage_attestation","attest_author":"https://pith.science/pith/KPZJBARMUBYBOCEQ6N7GFL2SX2/action/author_attestation","sign_citation":"https://pith.science/pith/KPZJBARMUBYBOCEQ6N7GFL2SX2/action/citation_signature","submit_replication":"https://pith.science/pith/KPZJBARMUBYBOCEQ6N7GFL2SX2/action/replication_record"}},"created_at":"2026-07-05T11:01:06.593432+00:00","updated_at":"2026-07-05T11:01:06.593432+00:00"}