{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JOB7ERJ3HU2FDLNTOGJ2JKI57J","short_pith_number":"pith:JOB7ERJ3","schema_version":"1.0","canonical_sha256":"4b83f2453b3d3451adb37193a4a91dfa66070ead4d72c602f1011d68c9c3926e","source":{"kind":"arxiv","id":"2305.04501","version":2},"attestation_state":"computed","paper":{"title":"SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bowen Shi, Junran Wu, Ke Xu, Shangzhe Li, Xueyuan Chen","submitted_at":"2023-05-08T06:52:02Z","abstract_excerpt":"In contrastive learning, the choice of ``view'' controls the information that the representation captures and influences the performance of the model. However, leading graph contrastive learning methods generally produce views via random corruption or learning, which could lead to the loss of essential information and alteration of semantic information. An anchor view that maintains the essential information of input graphs for contrastive learning has been hardly investigated. In this paper, based on the theory of graph information bottleneck, we deduce the definition of this anchor view; put"},"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":"2305.04501","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-08T06:52:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6dad803872da54dc5e5867d4fb74ad3a3f9b99a716ba6378666bfa73803037b1","abstract_canon_sha256":"21eee7f44934ecccaf4203466d6a18bedb60649bf11efa3d1477ddaeb9d2bc87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:03.949237Z","signature_b64":"kiW/68RKuYctyqJOuQ64zUy2UYiOKgIr4iRz4Vk63ZKIzzPa+D2uVsDvttUZwYt82u7C03dh082Vu6E318QVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b83f2453b3d3451adb37193a4a91dfa66070ead4d72c602f1011d68c9c3926e","last_reissued_at":"2026-07-05T06:19:03.948758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:03.948758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEGA: Structural Entropy Guided Anchor View for Graph Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bowen Shi, Junran Wu, Ke Xu, Shangzhe Li, Xueyuan Chen","submitted_at":"2023-05-08T06:52:02Z","abstract_excerpt":"In contrastive learning, the choice of ``view'' controls the information that the representation captures and influences the performance of the model. However, leading graph contrastive learning methods generally produce views via random corruption or learning, which could lead to the loss of essential information and alteration of semantic information. An anchor view that maintains the essential information of input graphs for contrastive learning has been hardly investigated. In this paper, based on the theory of graph information bottleneck, we deduce the definition of this anchor view; put"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04501","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/2305.04501/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":"2305.04501","created_at":"2026-07-05T06:19:03.948816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.04501v2","created_at":"2026-07-05T06:19:03.948816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04501","created_at":"2026-07-05T06:19:03.948816+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOB7ERJ3HU2F","created_at":"2026-07-05T06:19:03.948816+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOB7ERJ3HU2FDLNT","created_at":"2026-07-05T06:19:03.948816+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOB7ERJ3","created_at":"2026-07-05T06:19:03.948816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08841","citing_title":"Structural Entropy Guided Probabilistic Coding","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOB7ERJ3HU2FDLNTOGJ2JKI57J","json":"https://pith.science/pith/JOB7ERJ3HU2FDLNTOGJ2JKI57J.json","graph_json":"https://pith.science/api/pith-number/JOB7ERJ3HU2FDLNTOGJ2JKI57J/graph.json","events_json":"https://pith.science/api/pith-number/JOB7ERJ3HU2FDLNTOGJ2JKI57J/events.json","paper":"https://pith.science/paper/JOB7ERJ3"},"agent_actions":{"view_html":"https://pith.science/pith/JOB7ERJ3HU2FDLNTOGJ2JKI57J","download_json":"https://pith.science/pith/JOB7ERJ3HU2FDLNTOGJ2JKI57J.json","view_paper":"https://pith.science/paper/JOB7ERJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.04501&json=true","fetch_graph":"https://pith.science/api/pith-number/JOB7ERJ3HU2FDLNTOGJ2JKI57J/graph.json","fetch_events":"https://pith.science/api/pith-number/JOB7ERJ3HU2FDLNTOGJ2JKI57J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOB7ERJ3HU2FDLNTOGJ2JKI57J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOB7ERJ3HU2FDLNTOGJ2JKI57J/action/storage_attestation","attest_author":"https://pith.science/pith/JOB7ERJ3HU2FDLNTOGJ2JKI57J/action/author_attestation","sign_citation":"https://pith.science/pith/JOB7ERJ3HU2FDLNTOGJ2JKI57J/action/citation_signature","submit_replication":"https://pith.science/pith/JOB7ERJ3HU2FDLNTOGJ2JKI57J/action/replication_record"}},"created_at":"2026-07-05T06:19:03.948816+00:00","updated_at":"2026-07-05T06:19:03.948816+00:00"}