{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:52TCMRW6CDGCXUMTX7C7YFYYPU","short_pith_number":"pith:52TCMRW6","schema_version":"1.0","canonical_sha256":"eea62646de10cc2bd193bfc5fc17187d3ed38fccea7535f0234fd6b9a6ca8c55","source":{"kind":"arxiv","id":"2412.14451","version":1},"attestation_state":"computed","paper":{"title":"CLDG: Contrastive Learning on Dynamic Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Shi, Bo Dong, Haoyi Zhou, Qinghua Zheng, Teng Ma, Yiming Xu","submitted_at":"2024-12-19T01:59:24Z","abstract_excerpt":"The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a s"},"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":"2412.14451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T01:59:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6e72fd8e0a462f54a2583d6dbe7a680e23a5077536cbb255344503a17008f2e9","abstract_canon_sha256":"70c609e5cc457eecd2ddaafc72c1f81fd32ab627b7fa63d64b22a5459d10b2e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:47.399346Z","signature_b64":"MlX7Tr0mM7aXGASOwBWWJ5dPzYlVfWHXL/5WdcGbLFDAXnD1QNDhCR1ZjIaMkrb0hQd4kvLSZa8HlivTSIY0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eea62646de10cc2bd193bfc5fc17187d3ed38fccea7535f0234fd6b9a6ca8c55","last_reissued_at":"2026-07-05T09:51:47.398871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:47.398871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLDG: Contrastive Learning on Dynamic Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Shi, Bo Dong, Haoyi Zhou, Qinghua Zheng, Teng Ma, Yiming Xu","submitted_at":"2024-12-19T01:59:24Z","abstract_excerpt":"The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph's augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14451","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/2412.14451/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":"2412.14451","created_at":"2026-07-05T09:51:47.398930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14451v1","created_at":"2026-07-05T09:51:47.398930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14451","created_at":"2026-07-05T09:51:47.398930+00:00"},{"alias_kind":"pith_short_12","alias_value":"52TCMRW6CDGC","created_at":"2026-07-05T09:51:47.398930+00:00"},{"alias_kind":"pith_short_16","alias_value":"52TCMRW6CDGCXUMT","created_at":"2026-07-05T09:51:47.398930+00:00"},{"alias_kind":"pith_short_8","alias_value":"52TCMRW6","created_at":"2026-07-05T09:51:47.398930+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/52TCMRW6CDGCXUMTX7C7YFYYPU","json":"https://pith.science/pith/52TCMRW6CDGCXUMTX7C7YFYYPU.json","graph_json":"https://pith.science/api/pith-number/52TCMRW6CDGCXUMTX7C7YFYYPU/graph.json","events_json":"https://pith.science/api/pith-number/52TCMRW6CDGCXUMTX7C7YFYYPU/events.json","paper":"https://pith.science/paper/52TCMRW6"},"agent_actions":{"view_html":"https://pith.science/pith/52TCMRW6CDGCXUMTX7C7YFYYPU","download_json":"https://pith.science/pith/52TCMRW6CDGCXUMTX7C7YFYYPU.json","view_paper":"https://pith.science/paper/52TCMRW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14451&json=true","fetch_graph":"https://pith.science/api/pith-number/52TCMRW6CDGCXUMTX7C7YFYYPU/graph.json","fetch_events":"https://pith.science/api/pith-number/52TCMRW6CDGCXUMTX7C7YFYYPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52TCMRW6CDGCXUMTX7C7YFYYPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52TCMRW6CDGCXUMTX7C7YFYYPU/action/storage_attestation","attest_author":"https://pith.science/pith/52TCMRW6CDGCXUMTX7C7YFYYPU/action/author_attestation","sign_citation":"https://pith.science/pith/52TCMRW6CDGCXUMTX7C7YFYYPU/action/citation_signature","submit_replication":"https://pith.science/pith/52TCMRW6CDGCXUMTX7C7YFYYPU/action/replication_record"}},"created_at":"2026-07-05T09:51:47.398930+00:00","updated_at":"2026-07-05T09:51:47.398930+00:00"}