{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P45MXQOK56XPXLCSK6ZDN4JH77","short_pith_number":"pith:P45MXQOK","schema_version":"1.0","canonical_sha256":"7f3acbc1caefaefbac5257b236f127ffc6f0603424a99bba4b309f366e48212f","source":{"kind":"arxiv","id":"2605.27063","version":1},"attestation_state":"computed","paper":{"title":"Learning Dynamic Graph Representations through Timespan View Contrasts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Shi, Bo Dong, Xu Hua, Yiming Xu, Zhen Peng","submitted_at":"2026-05-26T14:15:04Z","abstract_excerpt":"The rich information underlying graphs has inspired further investigation of unsupervised graph representation. Existing studies mainly depend on node features and topological properties within static graphs to create self-supervised signals, neglecting the temporal components carried by real-world graph data, such as timestamps of edges. To overcome this limitation, this paper explores how to model temporal evolution on dynamic graphs elegantly. Specifically, we introduce a new inductive bias, namely temporal translation invariance, which illustrates the tendency of the identical node to keep"},"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":"2605.27063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T14:15:04Z","cross_cats_sorted":[],"title_canon_sha256":"d80a3e6f79615c73bd62b9fac4706d2ba05d22ccca7702e9fa0a45dade09d9d1","abstract_canon_sha256":"a95c4cd6eb5fcefcfc59d15905bafebcc127c18a3e326ab693b55ab38de0b97d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:26.527305Z","signature_b64":"lfXFM7JCL8M4kdrSRTSMEMbVaHnDxC/H8drENDeDI9T3tUHpY0Ozyo0+Fzg5o0PvyBM+IynDQNJkoIlzfei2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f3acbc1caefaefbac5257b236f127ffc6f0603424a99bba4b309f366e48212f","last_reissued_at":"2026-05-27T01:06:26.526795Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:26.526795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Dynamic Graph Representations through Timespan View Contrasts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Shi, Bo Dong, Xu Hua, Yiming Xu, Zhen Peng","submitted_at":"2026-05-26T14:15:04Z","abstract_excerpt":"The rich information underlying graphs has inspired further investigation of unsupervised graph representation. Existing studies mainly depend on node features and topological properties within static graphs to create self-supervised signals, neglecting the temporal components carried by real-world graph data, such as timestamps of edges. To overcome this limitation, this paper explores how to model temporal evolution on dynamic graphs elegantly. Specifically, we introduce a new inductive bias, namely temporal translation invariance, which illustrates the tendency of the identical node to keep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27063","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/2605.27063/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":"2605.27063","created_at":"2026-05-27T01:06:26.526866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27063v1","created_at":"2026-05-27T01:06:26.526866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27063","created_at":"2026-05-27T01:06:26.526866+00:00"},{"alias_kind":"pith_short_12","alias_value":"P45MXQOK56XP","created_at":"2026-05-27T01:06:26.526866+00:00"},{"alias_kind":"pith_short_16","alias_value":"P45MXQOK56XPXLCS","created_at":"2026-05-27T01:06:26.526866+00:00"},{"alias_kind":"pith_short_8","alias_value":"P45MXQOK","created_at":"2026-05-27T01:06:26.526866+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/P45MXQOK56XPXLCSK6ZDN4JH77","json":"https://pith.science/pith/P45MXQOK56XPXLCSK6ZDN4JH77.json","graph_json":"https://pith.science/api/pith-number/P45MXQOK56XPXLCSK6ZDN4JH77/graph.json","events_json":"https://pith.science/api/pith-number/P45MXQOK56XPXLCSK6ZDN4JH77/events.json","paper":"https://pith.science/paper/P45MXQOK"},"agent_actions":{"view_html":"https://pith.science/pith/P45MXQOK56XPXLCSK6ZDN4JH77","download_json":"https://pith.science/pith/P45MXQOK56XPXLCSK6ZDN4JH77.json","view_paper":"https://pith.science/paper/P45MXQOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27063&json=true","fetch_graph":"https://pith.science/api/pith-number/P45MXQOK56XPXLCSK6ZDN4JH77/graph.json","fetch_events":"https://pith.science/api/pith-number/P45MXQOK56XPXLCSK6ZDN4JH77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P45MXQOK56XPXLCSK6ZDN4JH77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P45MXQOK56XPXLCSK6ZDN4JH77/action/storage_attestation","attest_author":"https://pith.science/pith/P45MXQOK56XPXLCSK6ZDN4JH77/action/author_attestation","sign_citation":"https://pith.science/pith/P45MXQOK56XPXLCSK6ZDN4JH77/action/citation_signature","submit_replication":"https://pith.science/pith/P45MXQOK56XPXLCSK6ZDN4JH77/action/replication_record"}},"created_at":"2026-05-27T01:06:26.526866+00:00","updated_at":"2026-05-27T01:06:26.526866+00:00"}