{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DZAEASUU7SLUZPGBBVGBGLAC7J","short_pith_number":"pith:DZAEASUU","schema_version":"1.0","canonical_sha256":"1e40404a94fc974cbcc10d4c132c02fa762610265fc339eea47814fc51ff1405","source":{"kind":"arxiv","id":"2602.13075","version":2},"attestation_state":"computed","paper":{"title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chundong Liang, Di Jin, Dongxiao He, Peiyuan Li, Weixiong Zhang, Yawen Li, Yongqi Huang","submitted_at":"2026-02-13T16:34:55Z","abstract_excerpt":"Graph pre-training has achieved remarkable success in recent years, delivering transferable representations for downstream adaptation. However, most existing methods are designed for either homogeneous or heterogeneous graphs, thereby hindering unified graph modeling across diverse graph types. This separation contradicts real-world applications, where mixed homogeneous and heterogeneous graphs are ubiquitous, and distribution shifts between upstream pre-training and downstream deployment are common. In this paper, we empirically demonstrate that a balanced mixture of homogeneous and heterogen"},"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":"2602.13075","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-13T16:34:55Z","cross_cats_sorted":[],"title_canon_sha256":"c0308dde4c64292bf0351dd7a4593a692bd7f321ba636e76d3c088ff0c8ba711","abstract_canon_sha256":"fd3c603fed2f07f74a19c2f580512b223dc379c48d9407a464683b3c7f52d17d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:36.834499Z","signature_b64":"fG+SjPmiJoAMhDY0E2faRRX3JoNxWIB2a2S5qyzBBFfyX8/1Tlp/rG50ddfW01Bg2Y9Munn2YvzI6q5YVw7qCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e40404a94fc974cbcc10d4c132c02fa762610265fc339eea47814fc51ff1405","last_reissued_at":"2026-05-28T01:04:36.833973Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:36.833973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chundong Liang, Di Jin, Dongxiao He, Peiyuan Li, Weixiong Zhang, Yawen Li, Yongqi Huang","submitted_at":"2026-02-13T16:34:55Z","abstract_excerpt":"Graph pre-training has achieved remarkable success in recent years, delivering transferable representations for downstream adaptation. However, most existing methods are designed for either homogeneous or heterogeneous graphs, thereby hindering unified graph modeling across diverse graph types. This separation contradicts real-world applications, where mixed homogeneous and heterogeneous graphs are ubiquitous, and distribution shifts between upstream pre-training and downstream deployment are common. In this paper, we empirically demonstrate that a balanced mixture of homogeneous and heterogen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.13075","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/2602.13075/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":"2602.13075","created_at":"2026-05-28T01:04:36.834040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.13075v2","created_at":"2026-05-28T01:04:36.834040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.13075","created_at":"2026-05-28T01:04:36.834040+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZAEASUU7SLU","created_at":"2026-05-28T01:04:36.834040+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZAEASUU7SLUZPGB","created_at":"2026-05-28T01:04:36.834040+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZAEASUU","created_at":"2026-05-28T01:04:36.834040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15888","citing_title":"CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZAEASUU7SLUZPGBBVGBGLAC7J","json":"https://pith.science/pith/DZAEASUU7SLUZPGBBVGBGLAC7J.json","graph_json":"https://pith.science/api/pith-number/DZAEASUU7SLUZPGBBVGBGLAC7J/graph.json","events_json":"https://pith.science/api/pith-number/DZAEASUU7SLUZPGBBVGBGLAC7J/events.json","paper":"https://pith.science/paper/DZAEASUU"},"agent_actions":{"view_html":"https://pith.science/pith/DZAEASUU7SLUZPGBBVGBGLAC7J","download_json":"https://pith.science/pith/DZAEASUU7SLUZPGBBVGBGLAC7J.json","view_paper":"https://pith.science/paper/DZAEASUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.13075&json=true","fetch_graph":"https://pith.science/api/pith-number/DZAEASUU7SLUZPGBBVGBGLAC7J/graph.json","fetch_events":"https://pith.science/api/pith-number/DZAEASUU7SLUZPGBBVGBGLAC7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZAEASUU7SLUZPGBBVGBGLAC7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZAEASUU7SLUZPGBBVGBGLAC7J/action/storage_attestation","attest_author":"https://pith.science/pith/DZAEASUU7SLUZPGBBVGBGLAC7J/action/author_attestation","sign_citation":"https://pith.science/pith/DZAEASUU7SLUZPGBBVGBGLAC7J/action/citation_signature","submit_replication":"https://pith.science/pith/DZAEASUU7SLUZPGBBVGBGLAC7J/action/replication_record"}},"created_at":"2026-05-28T01:04:36.834040+00:00","updated_at":"2026-05-28T01:04:36.834040+00:00"}