{"as_of":"2026-08-10T00:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7426743fafb959a0ffe72654674633599d2a1695311fc20ddde43bbfc60c7cd9","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T10:38:33.135773Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T05:39:34.042152Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.09416","snapshot_observed_at":"2026-08-01T05:39:34.042152Z","title":"What do temporal graph learning models learn?","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.22781","last_updated":"2026-07-24T10:11:22Z","snapshot_observed_at":"2026-08-05T11:48:08.682165Z","submitted_at":"2026-07-24T10:11:22Z","title":"What Softmax Throws Away: Mass-Aware Attention for Evidence Accumulation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T05:39:34.042152Z"},"links":{"cited_paper":"/paper/2510.09416","citing_paper":"/paper/2607.22781"},"observation_digest":"sha256:73fe583853642b1ac1ff5d978afe15874258c72c65310c6a68ac46e58bb24671","observation_id":"3a0fad89-0582-4806-88ab-9fc9d9bb689e","resolution":{"observed_at":"2026-08-01T05:39:34.042152Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2510.09416/citation-record","integrity":"/paper/2510.09416/integrity","json":"/paper/2510.09416/citation-record.json","paper":"/paper/2510.09416"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:30.707999Z","title":"Emergence of Scaling in Random Networks","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:30.707999Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:fb0e89f6acd01fa43a2a0ef1cbfae615950c6910407e4a99773c141eec7ab0b7","observation_id":"b8001b92-98e9-48ef-8866-795aa3832838","resolution":{"observed_at":"2026-08-04T10:38:30.707999Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14546","last_updated":"2025-02-20T13:21:47Z","snapshot_observed_at":"2026-08-07T21:34:49.938980Z","submitted_at":"2025-02-20T13:21:47Z","title":"Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.14546","snapshot_observed_at":"2026-08-04T10:38:30.805401Z","title":"Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:30.805401Z"},"links":{"cited_paper":"/paper/2502.14546","citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:1cd66ea40c9b55e16a4e8c9739a7b6bc9fc08e9d66f022fa87dde0abc33bd7a9","observation_id":"c4831cfa-c57c-42e6-bd6f-02f4d5a21856","resolution":{"observed_at":"2026-08-04T10:38:30.805401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:30.889171Z","title":"Do We Really Need Complicated Model Architectures For Temporal Networks?","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:30.889171Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:ea523c68743ed077d17affce4cb6cbd8a1c48b9f81647801d8332d1c28b0d6ec","observation_id":"3d501d44-2142-42d7-a760-7bbd56f53e6a","resolution":{"observed_at":"2026-08-04T10:38:30.889171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.12588","last_updated":"2025-06-14T17:53:10Z","snapshot_observed_at":"2026-08-07T00:43:19.051831Z","submitted_at":"2025-06-14T17:53:10Z","title":"Are We Really Measuring Progress? Transferring Insights from Evaluating Recommender Systems to Temporal Link Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.12588","snapshot_observed_at":"2026-08-04T10:38:30.952590Z","title":"Are We Really Measuring Progress? Transferring Insights from Evaluating Recommender Systems to Temporal Link Prediction","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:30.952590Z"},"links":{"cited_paper":"/paper/2506.12588","citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:6c28b8995b0fba0e07036556f83418dc2f03e53facf08be6aad523ab47afc220","observation_id":"583710b1-b8bc-4ab2-a913-5091f7190b3a","resolution":{"observed_at":"2026-08-04T10:38:30.952590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.036764Z","title":"On the Power of Heuristics in Temporal Graphs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.036764Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:1fa626e63f5f812e1d3825ed6c02756a4ae0ae35fda50d63403a3e52ff5af02f","observation_id":"dbcf841b-1c4e-43e3-9c4e-34d3f8e57642","resolution":{"observed_at":"2026-08-04T10:38:31.036764Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.134745Z","title":"TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.134745Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:4fbce6e2d03a06748a6552beace514bf52eacc4309263486ac95da26e3d0aaf7","observation_id":"5615a2da-0a20-4cb9-bf45-7f51dd639876","resolution":{"observed_at":"2026-08-04T10:38:31.134745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.254737Z","title":"Deep Learning for Dynamic Graphs: Models and Benchmarks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.254737Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:9acd696c0ecf2efc518bc37350ab21febf070ca27c5223578da54332a00b1d51","observation_id":"3627c78d-eab5-47ca-a7cd-88fb71d14f3c","resolution":{"observed_at":"2026-08-04T10:38:31.254737Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.360673Z","title":"Stochastic blockmodels: First steps","venue":null,"work_id":null,"year":1983},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.360673Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:bc195caebd4d32c337ce46c3ec7d83197495467f7491dc18de3c870f9a07a06d","observation_id":"33e010e8-0718-4eeb-8c78-73b4dde6a242","resolution":{"observed_at":"2026-08-04T10:38:31.360673Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.464626Z","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.464626Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:2888c60696b79afcd938f68484b3667653a0c7818eef023334043ad92c608aae","observation_id":"e10f144c-5d54-4a8e-a5f9-14bac672b5a8","resolution":{"observed_at":"2026-08-04T10:38:31.464626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.514556Z","title":"Benchtemp: A General Benchmark for Evaluating Temporal Graph Neural Networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.514556Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:90016304031cdab826b0d143ac4084d94b74b9245808dbabeda31ea2b60f4b60","observation_id":"85f2826c-42ad-4a2e-a804-8bcbe9934111","resolution":{"observed_at":"2026-08-04T10:38:31.514556Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.575308Z","title":"Temporal Graph Benchmark for Machine Learning on Temporal Graphs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.575308Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:3442d46629f416ab60b4e57ab070760984aa3565ccc2c071dd1c35984cde645b","observation_id":"c0fd16fe-b8f4-43ee-be0b-69bde604bfbf","resolution":{"observed_at":"2026-08-04T10:38:31.575308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.634583Z","title":"UTG: Towards a Unified View of Snapshot and Event Based Models for Temporal Graphs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.634583Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:4fd544597b24a6d7dfaf29c2e50af122722708d16c00192c7a522076b8ccaf50","observation_id":"099eecc2-9911-4a22-88a6-cd7a8dee6dfe","resolution":{"observed_at":"2026-08-04T10:38:31.634583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.714742Z","title":"Homophily influences ranking of minorities in social networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.714742Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:d7333ac4a8a05b43b5895db58b3dcab5492fcc0000f370998a41c0a99a9922f9","observation_id":"e25c720e-af2a-41e6-93bc-d775a721b8e9","resolution":{"observed_at":"2026-08-04T10:38:31.714742Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.784337Z","title":"Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.784337Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:4834f5745667c7c484bebe9962d9b7856c5196768c034fde4826877b20859bcc","observation_id":"3347a1ca-1808-4e10-a374-128086b89e99","resolution":{"observed_at":"2026-08-04T10:38:31.784337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:31.894737Z","title":"Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmark- ing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:31.894737Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:b827e87943b3fb4e5ab8158fec8a43ba834e95c45cd1dd9326bb894ed4e41631","observation_id":"40ab0513-0852-43ba-a170-e792da8c3fcc","resolution":{"observed_at":"2026-08-04T10:38:31.894737Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:32.014804Z","title":"Patterns and dynamics of users’ behavior and interaction: Network analysis of an online community","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:32.014804Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:f02bd88181a572e1a335f3389dc168a95dc611b90652d3f04f9a7cfdbec33df2","observation_id":"f4a0698d-7e8b-45ee-8586-6156579f7f18","resolution":{"observed_at":"2026-08-04T10:38:32.014804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:32.124913Z","title":"Towards Better Evaluation for Dynamic Link Prediction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:32.124913Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:0783a4015d96e9dcbb6b724f3bbd22557d9f24142825bc00b4df3159e70e9a80","observation_id":"7d1b5956-66f6-4482-a335-ac73f7a0bcb7","resolution":{"observed_at":"2026-08-04T10:38:32.124913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:32.192428Z","title":"Rethinking Evaluation for Temporal Link Prediction through Counterfactual Analysis","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:32.192428Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:f2dd01358028259e8114bd1f373bfb8d563abeb5c4674e353f340fea1227ca81","observation_id":"5938bbfa-5751-4955-a817-96c090ed6f3f","resolution":{"observed_at":"2026-08-04T10:38:32.192428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:32.271009Z","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:32.271009Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:3fc3ea4b6affe54100e7f72afc12065fe7a21f3596eef9686c893e04d3931578","observation_id":"52e30a81-1979-45ee-be42-e408a191168f","resolution":{"observed_at":"2026-08-04T10:38:32.271009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:32.366294Z","title":"The Enron Email Dataset Database Schema and Brief Statistical Report","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:32.366294Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:7bcc9b3b8ac5bb18e9a18b7195e52e26cc9657452ce56000ba41b4a662432d70","observation_id":"f3d3fcd4-7d84-41d9-8eef-406b39ec6168","resolution":{"observed_at":"2026-08-04T10:38:32.366294Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:32.487177Z","title":"DyRep: Learning Representations over Dynamic Graphs","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:32.487177Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:229d72b41c61affd5285614df5f545649bac3ddfbaf56a4e53a9d6dbd195016f","observation_id":"320e78b5-fac7-46fd-9ea3-6f1860190880","resolution":{"observed_at":"2026-08-04T10:38:32.487177Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.07944","last_updated":"2021-05-17T15:33:25Z","snapshot_observed_at":"2026-08-07T20:17:21.322116Z","submitted_at":"2021-05-17T15:33:25Z","title":"TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.07944","snapshot_observed_at":"2026-08-04T10:38:32.605613Z","title":"TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:32.605613Z"},"links":{"cited_paper":"/paper/2105.07944","citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:f61ece9ba63a46889e48e7f5d6b2643959e7848fa5f8a6974d74b97e71f69c40","observation_id":"53a20774-10e2-448d-ba75-4af16123f698","resolution":{"observed_at":"2026-08-04T10:38:32.605613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:32.733134Z","title":"Inductive Representation Learning on Temporal Graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:32.733134Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:2e45581fd4aabc4935d29ae3e0e35c33a1e1c697bff0416749c9fc5a601728d9","observation_id":"a533062a-cdaa-48c9-9c4e-af4e90b4c121","resolution":{"observed_at":"2026-08-04T10:38:32.733134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:32.833594Z","title":"Evaluating link prediction methods","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:32.833594Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:d097e2eadd5d970459c095d9a1a16bbba9a5961ed2d903238e266ae7a87f5b49","observation_id":"88033167-efaa-48a2-9fdd-6fc9002cc403","resolution":{"observed_at":"2026-08-04T10:38:32.833594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:32.914745Z","title":"TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:32.914745Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:0de647404aced3ec758f0528031637c5329ef01c1e824361f1e08bf0f150e8bd","observation_id":"ee538411-146a-4e27-8ec0-4c822a06eee6","resolution":{"observed_at":"2026-08-04T10:38:32.914745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:33.056782Z","title":"Towards better dynamic graph learning: new architecture and unified library","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:33.056782Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:ab9b649c174fb248031e54599388c82994cef7c747427926e175aa41d7039fe3","observation_id":"a8ea4a92-6ccd-4638-8101-38c7138584e6","resolution":{"observed_at":"2026-08-04T10:38:33.056782Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:38:33.135773Z","title":"A survey of dynamic graph neural networks","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T10:38:33.135773Z"},"links":{"citing_paper":"/paper/2510.09416"},"observation_digest":"sha256:1d390e095fd9f5d3ccf8f45232994d2565935f11e60607200c0e4fef1400064a","observation_id":"9a976a82-3e91-48b9-8455-a66f2f54afe5","resolution":{"observed_at":"2026-08-04T10:38:33.135773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2510.09416","last_updated":"2026-07-15T15:14:01Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T05:57:22.835102Z","submitted_at":"2025-10-10T14:18:37Z","title":"What Do Temporal Graph Learning Models Learn?"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":27,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":27},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 1 inbound Pith citation observation for arXiv:2510.09416."}