{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6Y27XHQJVSOFJ7EH5WP3WD4U5Z","short_pith_number":"pith:6Y27XHQJ","schema_version":"1.0","canonical_sha256":"f635fb9e09ac9c54fc87ed9fbb0f94ee5cadccb2b813343039f332c5cea66ab8","source":{"kind":"arxiv","id":"2509.01541","version":1},"attestation_state":"computed","paper":{"title":"Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.soft"],"primary_cat":"cs.LG","authors_text":"Doruk Efe G\\\"okmen, Risi Kondor, Smayan Khanna, Vincenzo Vitelli","submitted_at":"2025-09-01T15:16:28Z","abstract_excerpt":"Graph Contrastive Learning (GCL) has emerged as a leading paradigm for self-supervised learning on graphs, with strong performance reported on standardized datasets and growing applications ranging from genomics to drug discovery. We ask a basic question: does GCL actually outperform untrained baselines? We find that GCL's advantage depends strongly on dataset size and task difficulty. On standard datasets, untrained Graph Neural Networks (GNNs), simple multilayer perceptrons, and even handcrafted statistics can rival or exceed GCL. On the large molecular dataset ogbg-molhiv, we observe a cros"},"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":"2509.01541","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-01T15:16:28Z","cross_cats_sorted":["cond-mat.soft"],"title_canon_sha256":"9e9dcddcd564a9633c0be3eea4bca82b83e2a8e4ebd98860d787857624997072","abstract_canon_sha256":"203519b8d81acd817fe08193b6e6a00a272ad2dd6535ba66d009d7edc511c934"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:18.089821Z","signature_b64":"dpmdxC+UJIWUdjE6kOX5X/vAoctSLjasSJeuqrYfcxdS+CH1wyde7mSxUPIZ+7cSRo/+Dgrw1TvsMH3UgcdtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f635fb9e09ac9c54fc87ed9fbb0f94ee5cadccb2b813343039f332c5cea66ab8","last_reissued_at":"2026-07-05T12:04:18.089106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:18.089106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.soft"],"primary_cat":"cs.LG","authors_text":"Doruk Efe G\\\"okmen, Risi Kondor, Smayan Khanna, Vincenzo Vitelli","submitted_at":"2025-09-01T15:16:28Z","abstract_excerpt":"Graph Contrastive Learning (GCL) has emerged as a leading paradigm for self-supervised learning on graphs, with strong performance reported on standardized datasets and growing applications ranging from genomics to drug discovery. We ask a basic question: does GCL actually outperform untrained baselines? We find that GCL's advantage depends strongly on dataset size and task difficulty. On standard datasets, untrained Graph Neural Networks (GNNs), simple multilayer perceptrons, and even handcrafted statistics can rival or exceed GCL. On the large molecular dataset ogbg-molhiv, we observe a cros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01541","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/2509.01541/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":"2509.01541","created_at":"2026-07-05T12:04:18.089217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01541v1","created_at":"2026-07-05T12:04:18.089217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01541","created_at":"2026-07-05T12:04:18.089217+00:00"},{"alias_kind":"pith_short_12","alias_value":"6Y27XHQJVSOF","created_at":"2026-07-05T12:04:18.089217+00:00"},{"alias_kind":"pith_short_16","alias_value":"6Y27XHQJVSOFJ7EH","created_at":"2026-07-05T12:04:18.089217+00:00"},{"alias_kind":"pith_short_8","alias_value":"6Y27XHQJ","created_at":"2026-07-05T12:04:18.089217+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/6Y27XHQJVSOFJ7EH5WP3WD4U5Z","json":"https://pith.science/pith/6Y27XHQJVSOFJ7EH5WP3WD4U5Z.json","graph_json":"https://pith.science/api/pith-number/6Y27XHQJVSOFJ7EH5WP3WD4U5Z/graph.json","events_json":"https://pith.science/api/pith-number/6Y27XHQJVSOFJ7EH5WP3WD4U5Z/events.json","paper":"https://pith.science/paper/6Y27XHQJ"},"agent_actions":{"view_html":"https://pith.science/pith/6Y27XHQJVSOFJ7EH5WP3WD4U5Z","download_json":"https://pith.science/pith/6Y27XHQJVSOFJ7EH5WP3WD4U5Z.json","view_paper":"https://pith.science/paper/6Y27XHQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01541&json=true","fetch_graph":"https://pith.science/api/pith-number/6Y27XHQJVSOFJ7EH5WP3WD4U5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/6Y27XHQJVSOFJ7EH5WP3WD4U5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6Y27XHQJVSOFJ7EH5WP3WD4U5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6Y27XHQJVSOFJ7EH5WP3WD4U5Z/action/storage_attestation","attest_author":"https://pith.science/pith/6Y27XHQJVSOFJ7EH5WP3WD4U5Z/action/author_attestation","sign_citation":"https://pith.science/pith/6Y27XHQJVSOFJ7EH5WP3WD4U5Z/action/citation_signature","submit_replication":"https://pith.science/pith/6Y27XHQJVSOFJ7EH5WP3WD4U5Z/action/replication_record"}},"created_at":"2026-07-05T12:04:18.089217+00:00","updated_at":"2026-07-05T12:04:18.089217+00:00"}