{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UVPIYMV3HKKAHCRSEJQNIXGUPU","short_pith_number":"pith:UVPIYMV3","canonical_record":{"source":{"id":"2605.12998","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:54:46Z","cross_cats_sorted":[],"title_canon_sha256":"e66405226b3f233c78297d8164d3ad69b66251c9a8344dce723edb5bb20a71b1","abstract_canon_sha256":"2e085b0040a60160621ff1492320a58627da50bec6e5a08459d01650b8ecc192"},"schema_version":"1.0"},"canonical_sha256":"a55e8c32bb3a94038a322260d45cd47d3e9ad589772390d3e9b512f1c7135cdf","source":{"kind":"arxiv","id":"2605.12998","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12998","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12998v2","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12998","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"UVPIYMV3HKKA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UVPIYMV3HKKAHCRS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UVPIYMV3","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UVPIYMV3HKKAHCRSEJQNIXGUPU","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12998","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:54:46Z","cross_cats_sorted":[],"title_canon_sha256":"e66405226b3f233c78297d8164d3ad69b66251c9a8344dce723edb5bb20a71b1","abstract_canon_sha256":"2e085b0040a60160621ff1492320a58627da50bec6e5a08459d01650b8ecc192"},"schema_version":"1.0"},"canonical_sha256":"a55e8c32bb3a94038a322260d45cd47d3e9ad589772390d3e9b512f1c7135cdf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:00.468908Z","signature_b64":"ZJzsoS8gCPhCZh8cn+gmRTzAh2XaI5SHMT+gLbtDLyRejxWvQDciNw9Qj+MByk2HKssgvxUkhZYKYzLFx55aDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a55e8c32bb3a94038a322260d45cd47d3e9ad589772390d3e9b512f1c7135cdf","last_reissued_at":"2026-05-18T03:09:00.468382Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:00.468382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12998","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Bfm5v3uYtM2R8Nfj7kKMrnReMx1Go7lpBJntoeTguZ0lZeKVyT8xWq3VDY1R0xZrIAsNAL4su5Kk4S4IAkNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T20:05:46.582790Z"},"content_sha256":"178abfbe7f1a5decb6801422e1fbbb3120288025323538f3672c4f9a9adf621d","schema_version":"1.0","event_id":"sha256:178abfbe7f1a5decb6801422e1fbbb3120288025323538f3672c4f9a9adf621d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UVPIYMV3HKKAHCRSEJQNIXGUPU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Many existing continual graph learning methods implicitly depend on task boundaries and degrade under continuous distribution shifts in task-free streams.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dongjin Song, Guiquan Sun, Jingchao Ni, Xikun Zhang","submitted_at":"2026-05-13T04:54:46Z","abstract_excerpt":"Continual graph learning (CGL) aims to learn from dynamically evolving graphs while mitigating catastrophic forgetting. Existing CGL approaches typically adopt a task-based formulation, where the data stream is partitioned into a sequence of discrete tasks with pre-defined boundaries. However, such assumptions rarely hold in real-world environments, where data distributions evolve continuously and task identity is often unavailable. To better reflect realistic non-stationary environments, we revisit continual graph learning from a task-free perspective. We propose a unified formulation that mo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our findings indicate that many existing approaches implicitly rely on task boundary information and struggle under realistic task-free graph streams.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Gaussian parameterization of transition dynamics between latent task distributions accurately captures the spectrum of real-world continuous distribution shifts in graph data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DRIFT benchmark shows substantial performance degradation for continual graph learning methods under task-free continuous distribution shifts modeled via Gaussian mixtures.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Many existing continual graph learning methods implicitly depend on task boundaries and degrade under continuous distribution shifts in task-free streams.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b7e567077d7062c3d3d931e9e87470aa1258a55f80f6ccb8f9283abc454d2da7"},"source":{"id":"2605.12998","kind":"arxiv","version":2},"verdict":{"id":"086289f7-17a4-4c91-a067-95e44fb45f61","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:42:58.834938Z","strongest_claim":"Our findings indicate that many existing approaches implicitly rely on task boundary information and struggle under realistic task-free graph streams.","one_line_summary":"DRIFT benchmark shows substantial performance degradation for continual graph learning methods under task-free continuous distribution shifts modeled via Gaussian mixtures.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Gaussian parameterization of transition dynamics between latent task distributions accurately captures the spectrum of real-world continuous distribution shifts in graph data.","pith_extraction_headline":"Many existing continual graph learning methods implicitly depend on task boundaries and degrade under continuous distribution shifts in task-free streams."},"references":{"count":51,"sample":[{"doi":"","year":2017,"title":"Inductive representation learning on large graphs","work_id":"ee217072-19c9-4225-b00c-43701e678a27","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Open graph benchmark: Datasets for machine learning on graphs","work_id":"39cc4a5f-a4c0-4922-a15f-e07bc2f727e8","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Knowledge graph embedding: A survey of approaches and applications.IEEE transactions on knowledge and data engineering, 29:2724– 2743, 2017","work_id":"f7234f26-5339-4a43-866a-dc905f24ca7a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Overcoming catastrophic forgetting in neural networks.Proceedings of the national academy of sciences, 114(13):3521–3526","work_id":"68b7964f-cd25-47e6-a060-52bbc86a995d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1902,"title":"Chaudhry et al","work_id":"001da84d-4329-4699-85e9-5431d143af9b","ref_index":5,"cited_arxiv_id":"1902.10486","is_internal_anchor":true}],"resolved_work":51,"snapshot_sha256":"b27d8fa8dbd02e8bdd2bfecf74b652ce5d94dd97daba7999229cbed6fac04de3","internal_anchors":4},"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":"086289f7-17a4-4c91-a067-95e44fb45f61"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OL7+6mec8oWZ5qx+ip2J3L5HFZ2rQ7VDdJrdG5/PAZHu8eIXmvRUBVGYYbkIedULFLbkTi2QN/p1fX4WOYc5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T20:05:46.583504Z"},"content_sha256":"77c9c862e3725760e695fa977092a77cee73845deacb2d4b2337d65fe7e7378e","schema_version":"1.0","event_id":"sha256:77c9c862e3725760e695fa977092a77cee73845deacb2d4b2337d65fe7e7378e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UVPIYMV3HKKAHCRSEJQNIXGUPU/bundle.json","state_url":"https://pith.science/pith/UVPIYMV3HKKAHCRSEJQNIXGUPU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UVPIYMV3HKKAHCRSEJQNIXGUPU/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":"2026-06-10T20:05:46Z","links":{"resolver":"https://pith.science/pith/UVPIYMV3HKKAHCRSEJQNIXGUPU","bundle":"https://pith.science/pith/UVPIYMV3HKKAHCRSEJQNIXGUPU/bundle.json","state":"https://pith.science/pith/UVPIYMV3HKKAHCRSEJQNIXGUPU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UVPIYMV3HKKAHCRSEJQNIXGUPU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UVPIYMV3HKKAHCRSEJQNIXGUPU","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":"2e085b0040a60160621ff1492320a58627da50bec6e5a08459d01650b8ecc192","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:54:46Z","title_canon_sha256":"e66405226b3f233c78297d8164d3ad69b66251c9a8344dce723edb5bb20a71b1"},"schema_version":"1.0","source":{"id":"2605.12998","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12998","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12998v2","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12998","created_at":"2026-05-18T03:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"UVPIYMV3HKKA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UVPIYMV3HKKAHCRS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UVPIYMV3","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:77c9c862e3725760e695fa977092a77cee73845deacb2d4b2337d65fe7e7378e","target":"graph","created_at":"2026-05-18T03:09:00Z","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":"Our findings indicate that many existing approaches implicitly rely on task boundary information and struggle under realistic task-free graph streams."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The Gaussian parameterization of transition dynamics between latent task distributions accurately captures the spectrum of real-world continuous distribution shifts in graph data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DRIFT benchmark shows substantial performance degradation for continual graph learning methods under task-free continuous distribution shifts modeled via Gaussian mixtures."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Many existing continual graph learning methods implicitly depend on task boundaries and degrade under continuous distribution shifts in task-free streams."}],"snapshot_sha256":"b7e567077d7062c3d3d931e9e87470aa1258a55f80f6ccb8f9283abc454d2da7"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Continual graph learning (CGL) aims to learn from dynamically evolving graphs while mitigating catastrophic forgetting. Existing CGL approaches typically adopt a task-based formulation, where the data stream is partitioned into a sequence of discrete tasks with pre-defined boundaries. However, such assumptions rarely hold in real-world environments, where data distributions evolve continuously and task identity is often unavailable. To better reflect realistic non-stationary environments, we revisit continual graph learning from a task-free perspective. We propose a unified formulation that mo","authors_text":"Dongjin Song, Guiquan Sun, Jingchao Ni, Xikun Zhang","cross_cats":[],"headline":"Many existing continual graph learning methods implicitly depend on task boundaries and degrade under continuous distribution shifts in task-free streams.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:54:46Z","title":"DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts"},"references":{"count":51,"internal_anchors":4,"resolved_work":51,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Inductive representation learning on large graphs","work_id":"ee217072-19c9-4225-b00c-43701e678a27","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Open graph benchmark: Datasets for machine learning on graphs","work_id":"39cc4a5f-a4c0-4922-a15f-e07bc2f727e8","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Knowledge graph embedding: A survey of approaches and applications.IEEE transactions on knowledge and data engineering, 29:2724– 2743, 2017","work_id":"f7234f26-5339-4a43-866a-dc905f24ca7a","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Overcoming catastrophic forgetting in neural networks.Proceedings of the national academy of sciences, 114(13):3521–3526","work_id":"68b7964f-cd25-47e6-a060-52bbc86a995d","year":2017},{"cited_arxiv_id":"1902.10486","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Chaudhry et al","work_id":"001da84d-4329-4699-85e9-5431d143af9b","year":1902}],"snapshot_sha256":"b27d8fa8dbd02e8bdd2bfecf74b652ce5d94dd97daba7999229cbed6fac04de3"},"source":{"id":"2605.12998","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T05:42:58.834938Z","id":"086289f7-17a4-4c91-a067-95e44fb45f61","model_set":{"reader":"grok-4.3"},"one_line_summary":"DRIFT benchmark shows substantial performance degradation for continual graph learning methods under task-free continuous distribution shifts modeled via Gaussian mixtures.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Many existing continual graph learning methods implicitly depend on task boundaries and degrade under continuous distribution shifts in task-free streams.","strongest_claim":"Our findings indicate that many existing approaches implicitly rely on task boundary information and struggle under realistic task-free graph streams.","weakest_assumption":"The Gaussian parameterization of transition dynamics between latent task distributions accurately captures the spectrum of real-world continuous distribution shifts in graph data."}},"verdict_id":"086289f7-17a4-4c91-a067-95e44fb45f61"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:178abfbe7f1a5decb6801422e1fbbb3120288025323538f3672c4f9a9adf621d","target":"record","created_at":"2026-05-18T03:09:00Z","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":"2e085b0040a60160621ff1492320a58627da50bec6e5a08459d01650b8ecc192","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:54:46Z","title_canon_sha256":"e66405226b3f233c78297d8164d3ad69b66251c9a8344dce723edb5bb20a71b1"},"schema_version":"1.0","source":{"id":"2605.12998","kind":"arxiv","version":2}},"canonical_sha256":"a55e8c32bb3a94038a322260d45cd47d3e9ad589772390d3e9b512f1c7135cdf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a55e8c32bb3a94038a322260d45cd47d3e9ad589772390d3e9b512f1c7135cdf","first_computed_at":"2026-05-18T03:09:00.468382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:00.468382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZJzsoS8gCPhCZh8cn+gmRTzAh2XaI5SHMT+gLbtDLyRejxWvQDciNw9Qj+MByk2HKssgvxUkhZYKYzLFx55aDw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:00.468908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12998","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:178abfbe7f1a5decb6801422e1fbbb3120288025323538f3672c4f9a9adf621d","sha256:77c9c862e3725760e695fa977092a77cee73845deacb2d4b2337d65fe7e7378e"],"state_sha256":"ac7a7dad49e833d569e5691c8506d6b2c958b993e8c6b6c4315132bf72fa7bc9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NIjnQOm2WqsjLdYfxcfWrx+4nojLPYx6OlN2oNTvjy33G9WGLHmMKRLKKOokzzbMaYerAn+LrgwU+MIiTEgXAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T20:05:46.586258Z","bundle_sha256":"65eb77f71d166e3c4ff45d59627c3d8e78bf85d03d0b2c152fd259e0e6249267"}}