{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J5ZOWQD5VWHPS4UOCOV7SXQYRK","short_pith_number":"pith:J5ZOWQD5","schema_version":"1.0","canonical_sha256":"4f72eb407dad8ef9728e13abf95e188a9dc58646360acc0bf705b0444bb60fdc","source":{"kind":"arxiv","id":"2605.13540","version":1},"attestation_state":"computed","paper":{"title":"Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"DyGFM decouples semantic and temporal patterns in dynamic graphs and uses divergence-conditioned prompts to enable effective multi-domain pre-training without negative transfer.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haonan Yuan, Jianxin Li, Junhua Shi, Philip S. Yu, Qingyun Sun, Xingcheng Fu","submitted_at":"2026-05-13T13:50:03Z","abstract_excerpt":"Dynamic graphs are ubiquitous in real-world systems, and building generalizable dynamic Graph Foundation Models has become a frontier in graph learning. However, dynamic graphs from different domains pose fundamental challenges to unified modeling, as their semantic and temporal patterns are inherently inconsistent, making the multi-domain pre-training difficult. Consequently, the widely used \"pretrain-then-finetune\" paradigm often suffers from severe negative knowledge transfer. To the best of our knowledge, there exists no multi-domain dynamic GFM. In this work, we propose DyGFM, a Dynamic G"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T13:50:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"887ecaf0a67b021a20cab2fbc1d0a1adc0dabbb7aa1ba6e05dff9e2b22358658","abstract_canon_sha256":"0a9739fbea1ccaec48cc3bc52a1cdf220a7fcca8d38981d0b000bd0319dc3989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:24.057764Z","signature_b64":"u5AH8kFadVXZuf9DJLAPUNp35Iw7XMHJsB4LYPr8TyLfYVS7XngeWfDZGo2g/X3BFT/zCxaeLy5L8k8nqXWrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f72eb407dad8ef9728e13abf95e188a9dc58646360acc0bf705b0444bb60fdc","last_reissued_at":"2026-05-18T02:44:24.057293Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:24.057293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"DyGFM decouples semantic and temporal patterns in dynamic graphs and uses divergence-conditioned prompts to enable effective multi-domain pre-training without negative transfer.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haonan Yuan, Jianxin Li, Junhua Shi, Philip S. Yu, Qingyun Sun, Xingcheng Fu","submitted_at":"2026-05-13T13:50:03Z","abstract_excerpt":"Dynamic graphs are ubiquitous in real-world systems, and building generalizable dynamic Graph Foundation Models has become a frontier in graph learning. However, dynamic graphs from different domains pose fundamental challenges to unified modeling, as their semantic and temporal patterns are inherently inconsistent, making the multi-domain pre-training difficult. Consequently, the widely used \"pretrain-then-finetune\" paradigm often suffers from severe negative knowledge transfer. To the best of our knowledge, there exists no multi-domain dynamic GFM. In this work, we propose DyGFM, a Dynamic G"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"DyGFM consistently outperforms 12 state-of-the-art baselines on both node classification and link prediction tasks, achieving superior effectiveness and efficiency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that semantic-temporal decoupling plus divergence-aware expert selection will reliably prevent negative transfer across arbitrary domains without introducing new biases or requiring extensive hyperparameter tuning per domain pair.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DyGFM introduces decoupled pre-training and divergence-conditioned prompts to create the first multi-domain dynamic graph foundation model that outperforms baselines on node classification and link prediction.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DyGFM decouples semantic and temporal patterns in dynamic graphs and uses divergence-conditioned prompts to enable effective multi-domain pre-training without negative transfer.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0ec6571c7fa281cf22c3946cf8230904259a2c4e2e4e3c031c0547afa51b4bfe"},"source":{"id":"2605.13540","kind":"arxiv","version":1},"verdict":{"id":"8315ce0c-0a13-4545-b3d4-f17c1e715768","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:18:30.424750Z","strongest_claim":"DyGFM consistently outperforms 12 state-of-the-art baselines on both node classification and link prediction tasks, achieving superior effectiveness and efficiency.","one_line_summary":"DyGFM introduces decoupled pre-training and divergence-conditioned prompts to create the first multi-domain dynamic graph foundation model that outperforms baselines on node classification and link prediction.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that semantic-temporal decoupling plus divergence-aware expert selection will reliably prevent negative transfer across arbitrary domains without introducing new biases or requiring extensive hyperparameter tuning per domain pair.","pith_extraction_headline":"DyGFM decouples semantic and temporal patterns in dynamic graphs and uses divergence-conditioned prompts to enable effective multi-domain pre-training without negative transfer."},"references":{"count":122,"sample":[{"doi":"","year":2002,"title":"Random graph models of social networks,","work_id":"d1a7ac2e-1bbe-4116-9417-a74108fce148","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Graph neural networks for social recommendation,","work_id":"5b2cba34-653a-4e9f-81c0-b2003455ae89","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Graph neural networks for friend ranking in large-scale social platforms,","work_id":"86b6b116-f9cb-41ed-924b-99a9af6187d9","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Graph convolutional neural networks for web-scale recommender systems,","work_id":"4fa665f5-4881-4183-b3f3-c7ef4d9340eb","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Session-based recommendation with graph neural networks,","work_id":"ab77aff2-4abf-4b7d-ad28-d3bd7a463e9c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":122,"snapshot_sha256":"67f01850ce2c6f723006ab0b4d2f5e5f4f324c8bcf0451147af0490639e9a2d7","internal_anchors":5},"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":"2605.13540","created_at":"2026-05-18T02:44:24.057383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13540v1","created_at":"2026-05-18T02:44:24.057383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13540","created_at":"2026-05-18T02:44:24.057383+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5ZOWQD5VWHP","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5ZOWQD5VWHPS4UO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5ZOWQD5","created_at":"2026-05-18T12:33:37.589309+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/J5ZOWQD5VWHPS4UOCOV7SXQYRK","json":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK.json","graph_json":"https://pith.science/api/pith-number/J5ZOWQD5VWHPS4UOCOV7SXQYRK/graph.json","events_json":"https://pith.science/api/pith-number/J5ZOWQD5VWHPS4UOCOV7SXQYRK/events.json","paper":"https://pith.science/paper/J5ZOWQD5"},"agent_actions":{"view_html":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK","download_json":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK.json","view_paper":"https://pith.science/paper/J5ZOWQD5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13540&json=true","fetch_graph":"https://pith.science/api/pith-number/J5ZOWQD5VWHPS4UOCOV7SXQYRK/graph.json","fetch_events":"https://pith.science/api/pith-number/J5ZOWQD5VWHPS4UOCOV7SXQYRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/action/storage_attestation","attest_author":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/action/author_attestation","sign_citation":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/action/citation_signature","submit_replication":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/action/replication_record"}},"created_at":"2026-05-18T02:44:24.057383+00:00","updated_at":"2026-05-18T02:44:24.057383+00:00"}