{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HROHKUWSFJZIE357IH34UWBYNS","short_pith_number":"pith:HROHKUWS","schema_version":"1.0","canonical_sha256":"3c5c7552d22a72826fbf41f7ca58386c91ca4ddab5139411968d2f26269e1c69","source":{"kind":"arxiv","id":"2408.11243","version":2},"attestation_state":"computed","paper":{"title":"Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chunlin Feng, Haitao Mao, Jingzhe Liu, Qian Ma, Yao Ma, Yihan Shao, Yu Song, Zhehua Zhang","submitted_at":"2024-08-20T23:45:11Z","abstract_excerpt":"Self-supervised learning~(SSL) is essential to obtain foundation models in NLP and CV domains via effectively leveraging knowledge in large-scale unlabeled data. The reason for its success is that a suitable SSL design can help the model to follow the neural scaling law, i.e., the performance consistently improves with increasing model and dataset sizes. However, it remains a mystery whether existing SSL in the graph domain can follow the scaling behavior toward building Graph Foundation Models~(GFMs) with large-scale pre-training. In this study, we examine whether existing graph SSL technique"},"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":"2408.11243","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-20T23:45:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"310a6f45bc5e4e8794c5782c328ad67b7ca8b4ee868b7f5f758c64c28f1c93e6","abstract_canon_sha256":"eba1141f85ef583e5d8ec72775913ce47a1eaa8b84c43e96ef803183e356e3c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:32.718459Z","signature_b64":"tEzDOpmco6P+Hfw4Z5iQrxtYjLBGDtsStpe4n6r+z8S5sYFEcrPDfq1U+89Z2o+s00tCS2M8E+mvhwqQehSqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c5c7552d22a72826fbf41f7ca58386c91ca4ddab5139411968d2f26269e1c69","last_reissued_at":"2026-07-05T08:59:32.717949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:32.717949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Neural Scaling Laws Exist on Graph Self-Supervised Learning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chunlin Feng, Haitao Mao, Jingzhe Liu, Qian Ma, Yao Ma, Yihan Shao, Yu Song, Zhehua Zhang","submitted_at":"2024-08-20T23:45:11Z","abstract_excerpt":"Self-supervised learning~(SSL) is essential to obtain foundation models in NLP and CV domains via effectively leveraging knowledge in large-scale unlabeled data. The reason for its success is that a suitable SSL design can help the model to follow the neural scaling law, i.e., the performance consistently improves with increasing model and dataset sizes. However, it remains a mystery whether existing SSL in the graph domain can follow the scaling behavior toward building Graph Foundation Models~(GFMs) with large-scale pre-training. In this study, we examine whether existing graph SSL technique"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11243","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/2408.11243/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":"2408.11243","created_at":"2026-07-05T08:59:32.718019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11243v2","created_at":"2026-07-05T08:59:32.718019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11243","created_at":"2026-07-05T08:59:32.718019+00:00"},{"alias_kind":"pith_short_12","alias_value":"HROHKUWSFJZI","created_at":"2026-07-05T08:59:32.718019+00:00"},{"alias_kind":"pith_short_16","alias_value":"HROHKUWSFJZIE357","created_at":"2026-07-05T08:59:32.718019+00:00"},{"alias_kind":"pith_short_8","alias_value":"HROHKUWS","created_at":"2026-07-05T08:59:32.718019+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12061","citing_title":"SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HROHKUWSFJZIE357IH34UWBYNS","json":"https://pith.science/pith/HROHKUWSFJZIE357IH34UWBYNS.json","graph_json":"https://pith.science/api/pith-number/HROHKUWSFJZIE357IH34UWBYNS/graph.json","events_json":"https://pith.science/api/pith-number/HROHKUWSFJZIE357IH34UWBYNS/events.json","paper":"https://pith.science/paper/HROHKUWS"},"agent_actions":{"view_html":"https://pith.science/pith/HROHKUWSFJZIE357IH34UWBYNS","download_json":"https://pith.science/pith/HROHKUWSFJZIE357IH34UWBYNS.json","view_paper":"https://pith.science/paper/HROHKUWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11243&json=true","fetch_graph":"https://pith.science/api/pith-number/HROHKUWSFJZIE357IH34UWBYNS/graph.json","fetch_events":"https://pith.science/api/pith-number/HROHKUWSFJZIE357IH34UWBYNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HROHKUWSFJZIE357IH34UWBYNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HROHKUWSFJZIE357IH34UWBYNS/action/storage_attestation","attest_author":"https://pith.science/pith/HROHKUWSFJZIE357IH34UWBYNS/action/author_attestation","sign_citation":"https://pith.science/pith/HROHKUWSFJZIE357IH34UWBYNS/action/citation_signature","submit_replication":"https://pith.science/pith/HROHKUWSFJZIE357IH34UWBYNS/action/replication_record"}},"created_at":"2026-07-05T08:59:32.718019+00:00","updated_at":"2026-07-05T08:59:32.718019+00:00"}