{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DBLXTKVXM3CXHDT4ZFZF25R4OF","short_pith_number":"pith:DBLXTKVX","schema_version":"1.0","canonical_sha256":"185779aab766c5738e7cc9725d763c7153f4703f9d4534b69062d196db54f637","source":{"kind":"arxiv","id":"2212.07035","version":1},"attestation_state":"computed","paper":{"title":"MA-GCL: Model Augmentation Tricks for Graph Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng Yang, Chuan Shi, Xumeng Gong","submitted_at":"2022-12-14T05:04:10Z","abstract_excerpt":"Contrastive learning (CL), which can extract the information shared between different contrastive views, has become a popular paradigm for vision representation learning. Inspired by the success in computer vision, recent work introduces CL into graph modeling, dubbed as graph contrastive learning (GCL). However, generating contrastive views in graphs is more challenging than that in images, since we have little prior knowledge on how to significantly augment a graph without changing its labels. We argue that typical data augmentation techniques (e.g., edge dropping) in GCL cannot generate div"},"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":"2212.07035","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T05:04:10Z","cross_cats_sorted":[],"title_canon_sha256":"2ded86cc9f14fa4daf8ad0774dbeb46624a8cd40648e4f7202ecc266b8a149a3","abstract_canon_sha256":"8a3c8d141321db6e4971f56f729dc9fff1deaeb7762ca39e32b9a543b7da9f78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:20.210205Z","signature_b64":"h8RfvlypjEr6IK00Lymn8XFrad6HZ6VmAALHFcAUXBTAQYTtsiqq0ysIgTqKlG+0iI0DHKVoj9z8n5V8PAvQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"185779aab766c5738e7cc9725d763c7153f4703f9d4534b69062d196db54f637","last_reissued_at":"2026-07-05T05:25:20.209830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:20.209830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MA-GCL: Model Augmentation Tricks for Graph Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng Yang, Chuan Shi, Xumeng Gong","submitted_at":"2022-12-14T05:04:10Z","abstract_excerpt":"Contrastive learning (CL), which can extract the information shared between different contrastive views, has become a popular paradigm for vision representation learning. Inspired by the success in computer vision, recent work introduces CL into graph modeling, dubbed as graph contrastive learning (GCL). However, generating contrastive views in graphs is more challenging than that in images, since we have little prior knowledge on how to significantly augment a graph without changing its labels. We argue that typical data augmentation techniques (e.g., edge dropping) in GCL cannot generate div"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07035","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/2212.07035/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":"2212.07035","created_at":"2026-07-05T05:25:20.209882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07035v1","created_at":"2026-07-05T05:25:20.209882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07035","created_at":"2026-07-05T05:25:20.209882+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBLXTKVXM3CX","created_at":"2026-07-05T05:25:20.209882+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBLXTKVXM3CXHDT4","created_at":"2026-07-05T05:25:20.209882+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBLXTKVX","created_at":"2026-07-05T05:25:20.209882+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/DBLXTKVXM3CXHDT4ZFZF25R4OF","json":"https://pith.science/pith/DBLXTKVXM3CXHDT4ZFZF25R4OF.json","graph_json":"https://pith.science/api/pith-number/DBLXTKVXM3CXHDT4ZFZF25R4OF/graph.json","events_json":"https://pith.science/api/pith-number/DBLXTKVXM3CXHDT4ZFZF25R4OF/events.json","paper":"https://pith.science/paper/DBLXTKVX"},"agent_actions":{"view_html":"https://pith.science/pith/DBLXTKVXM3CXHDT4ZFZF25R4OF","download_json":"https://pith.science/pith/DBLXTKVXM3CXHDT4ZFZF25R4OF.json","view_paper":"https://pith.science/paper/DBLXTKVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07035&json=true","fetch_graph":"https://pith.science/api/pith-number/DBLXTKVXM3CXHDT4ZFZF25R4OF/graph.json","fetch_events":"https://pith.science/api/pith-number/DBLXTKVXM3CXHDT4ZFZF25R4OF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBLXTKVXM3CXHDT4ZFZF25R4OF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBLXTKVXM3CXHDT4ZFZF25R4OF/action/storage_attestation","attest_author":"https://pith.science/pith/DBLXTKVXM3CXHDT4ZFZF25R4OF/action/author_attestation","sign_citation":"https://pith.science/pith/DBLXTKVXM3CXHDT4ZFZF25R4OF/action/citation_signature","submit_replication":"https://pith.science/pith/DBLXTKVXM3CXHDT4ZFZF25R4OF/action/replication_record"}},"created_at":"2026-07-05T05:25:20.209882+00:00","updated_at":"2026-07-05T05:25:20.209882+00:00"}