{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:J5ZOWQD5VWHPS4UOCOV7SXQYRK","short_pith_number":"pith:J5ZOWQD5","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"},"canonical_sha256":"4f72eb407dad8ef9728e13abf95e188a9dc58646360acc0bf705b0444bb60fdc","source":{"kind":"arxiv","id":"2605.13540","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13540","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13540v1","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13540","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"J5ZOWQD5VWHP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"J5ZOWQD5VWHPS4UO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"J5ZOWQD5","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:J5ZOWQD5VWHPS4UOCOV7SXQYRK","target":"record","payload":{"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"},"canonical_sha256":"4f72eb407dad8ef9728e13abf95e188a9dc58646360acc0bf705b0444bb60fdc","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"},"source_kind":"arxiv","source_id":"2605.13540","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"frTD9bMWzCvS5D4n3Q+FEvCydot49n0D0KZtSLDYyoxlwkc1kaKoT6A/hU0CiVuak/ddaYpMTEDSIlWrj2fhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T19:04:02.560410Z"},"content_sha256":"d1a346f565cba730f472d46d48a1d269f8aeb7df3aa3a8da60860cfccb1a2dfc","schema_version":"1.0","event_id":"sha256:d1a346f565cba730f472d46d48a1d269f8aeb7df3aa3a8da60860cfccb1a2dfc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:J5ZOWQD5VWHPS4UOCOV7SXQYRK","target":"graph","payload":{"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"},"verdict_id":"8315ce0c-0a13-4545-b3d4-f17c1e715768"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMRbdcZnklh43GY5TZyjsJygbWJUOmNuq266YlCES1f/7h4hjU/Fq5OBhFm+t7EsNimjgXsGdrURf/lySGIpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T19:04:02.560954Z"},"content_sha256":"9ee1d4e1fa9bcfe5f160940a275292379088d81d0ab3895df22eb79521c8eeea","schema_version":"1.0","event_id":"sha256:9ee1d4e1fa9bcfe5f160940a275292379088d81d0ab3895df22eb79521c8eeea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/bundle.json","state_url":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T19:04:02Z","links":{"resolver":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK","bundle":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/bundle.json","state":"https://pith.science/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5ZOWQD5VWHPS4UOCOV7SXQYRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:J5ZOWQD5VWHPS4UOCOV7SXQYRK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0a9739fbea1ccaec48cc3bc52a1cdf220a7fcca8d38981d0b000bd0319dc3989","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T13:50:03Z","title_canon_sha256":"887ecaf0a67b021a20cab2fbc1d0a1adc0dabbb7aa1ba6e05dff9e2b22358658"},"schema_version":"1.0","source":{"id":"2605.13540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13540","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13540v1","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13540","created_at":"2026-05-18T02:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"J5ZOWQD5VWHP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"J5ZOWQD5VWHPS4UO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"J5ZOWQD5","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:9ee1d4e1fa9bcfe5f160940a275292379088d81d0ab3895df22eb79521c8eeea","target":"graph","created_at":"2026-05-18T02:44:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"DyGFM consistently outperforms 12 state-of-the-art baselines on both node classification and link prediction tasks, achieving superior effectiveness and efficiency."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"0ec6571c7fa281cf22c3946cf8230904259a2c4e2e4e3c031c0547afa51b4bfe"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Haonan Yuan, Jianxin Li, Junhua Shi, Philip S. Yu, Qingyun Sun, Xingcheng Fu","cross_cats":["cs.AI"],"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.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T13:50:03Z","title":"Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models"},"references":{"count":122,"internal_anchors":5,"resolved_work":122,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Random graph models of social networks,","work_id":"d1a7ac2e-1bbe-4116-9417-a74108fce148","year":2002},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Graph neural networks for social recommendation,","work_id":"5b2cba34-653a-4e9f-81c0-b2003455ae89","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Graph neural networks for friend ranking in large-scale social platforms,","work_id":"86b6b116-f9cb-41ed-924b-99a9af6187d9","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Graph convolutional neural networks for web-scale recommender systems,","work_id":"4fa665f5-4881-4183-b3f3-c7ef4d9340eb","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Session-based recommendation with graph neural networks,","work_id":"ab77aff2-4abf-4b7d-ad28-d3bd7a463e9c","year":2019}],"snapshot_sha256":"67f01850ce2c6f723006ab0b4d2f5e5f4f324c8bcf0451147af0490639e9a2d7"},"source":{"id":"2605.13540","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:18:30.424750Z","id":"8315ce0c-0a13-4545-b3d4-f17c1e715768","model_set":{"reader":"grok-4.3"},"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","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.","strongest_claim":"DyGFM consistently outperforms 12 state-of-the-art baselines on both node classification and link prediction tasks, achieving superior effectiveness and efficiency.","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."}},"verdict_id":"8315ce0c-0a13-4545-b3d4-f17c1e715768"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d1a346f565cba730f472d46d48a1d269f8aeb7df3aa3a8da60860cfccb1a2dfc","target":"record","created_at":"2026-05-18T02:44:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0a9739fbea1ccaec48cc3bc52a1cdf220a7fcca8d38981d0b000bd0319dc3989","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T13:50:03Z","title_canon_sha256":"887ecaf0a67b021a20cab2fbc1d0a1adc0dabbb7aa1ba6e05dff9e2b22358658"},"schema_version":"1.0","source":{"id":"2605.13540","kind":"arxiv","version":1}},"canonical_sha256":"4f72eb407dad8ef9728e13abf95e188a9dc58646360acc0bf705b0444bb60fdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f72eb407dad8ef9728e13abf95e188a9dc58646360acc0bf705b0444bb60fdc","first_computed_at":"2026-05-18T02:44:24.057293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:24.057293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u5AH8kFadVXZuf9DJLAPUNp35Iw7XMHJsB4LYPr8TyLfYVS7XngeWfDZGo2g/X3BFT/zCxaeLy5L8k8nqXWrDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:24.057764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1a346f565cba730f472d46d48a1d269f8aeb7df3aa3a8da60860cfccb1a2dfc","sha256:9ee1d4e1fa9bcfe5f160940a275292379088d81d0ab3895df22eb79521c8eeea"],"state_sha256":"dbd1cc67c39dbfce6813a3c5466964bf5ebbe5a604c8fc79617ef2fde09a445b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pUf3+GVuui2XBJ7GhipI6t4va4aFYMgBJ+Rxn6ijgeIfV9YF1x2oTOrAcCgvE5IQ4yQIsC0ry6csY+m0e01UDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T19:04:02.563586Z","bundle_sha256":"30e8fc959c0275d4125bf9c6b7ede198eefeaf82b064fd64fba1ef88bfe53118"}}