{"as_of":"2026-08-15T23:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a7feec1d33770b039eb90bc05e8905c820e2fd0e124702f7e1e00f45a0802b35","coverage":[{"denominator":93,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":93,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T14:06:18.661273Z","state":"measured"},{"denominator":97,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":97,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:48:40.606729Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T01:27:31.658024Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.12456","snapshot_observed_at":"2026-08-06T19:48:40.606729Z","title":"Graph learning in the era of llms: A survey from the perspective of data, models, and tasks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.16826","last_updated":"2025-07-07T02:22:54Z","snapshot_observed_at":"2026-08-13T05:28:47.067180Z","submitted_at":"2025-07-07T02:22:54Z","title":"A Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval-Augmented Generation in Large Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T19:48:40.606729Z"},"links":{"cited_paper":"/paper/2412.12456","citing_paper":"/paper/2507.16826"},"observation_digest":"sha256:a721eeb37d96c37622aca96a57f6e06d68c6defd76e07da7ac9e44b1cac6cf73","observation_id":"b621706a-0338-4c6e-899b-905a84d0d1a9","resolution":{"observed_at":"2026-08-06T19:48:40.606729Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.12456","snapshot_observed_at":"2026-08-04T19:59:17.174007Z","title":"Graph learning in the era of llms: A survey from the perspective of data, models, and tasks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.08950","last_updated":"2025-09-10T19:19:26Z","snapshot_observed_at":"2026-08-13T14:47:17.829502Z","submitted_at":"2025-09-10T19:19:26Z","title":"Deploying AI for Signal Processing education: Selected challenges and intriguing opportunities","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T19:59:17.174007Z"},"links":{"cited_paper":"/paper/2412.12456","citing_paper":"/paper/2509.08950"},"observation_digest":"sha256:097693a7fd483878a5fb2cc82074f69797f2ee5ffd67b519cb26fc1a153c5d4f","observation_id":"433384d8-1280-474f-b8eb-6f22e45a88a1","resolution":{"observed_at":"2026-08-04T19:59:17.174007Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"cited_work":{"arxiv_id":"2412.12456","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.12456","snapshot_observed_at":"2026-07-03T01:27:31.658024Z","title":"arXiv preprint arXiv:2412.12456 , year=","venue":null,"work_id":"82215743-892c-468e-91ad-65492b482133","year":2024},"citing_paper":{"arxiv_id":"2510.08952","last_updated":"2026-05-05T05:35:19Z","snapshot_observed_at":"2026-08-13T22:15:07.964383Z","submitted_at":"2025-10-10T02:59:19Z","title":"When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-18T08:45:51.992431Z"},"links":{"cited_paper":"/paper/2412.12456","citing_paper":"/paper/2510.08952"},"observation_digest":"sha256:84fa721c06e6be3d6bd0728fc71fb816a35e73ec3c4b3202cce85dc01f02c5cf","observation_id":"555857fc-c403-45a3-866c-44a54fb63d73","resolution":{"observed_at":"2026-05-18T08:46:07.752164Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"cited_work":{"arxiv_id":"2412.12456","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.12456","snapshot_observed_at":"2026-07-03T01:27:31.658024Z","title":"arXiv preprint arXiv:2412.12456 , year=","venue":null,"work_id":"82215743-892c-468e-91ad-65492b482133","year":2024},"citing_paper":{"arxiv_id":"2606.09484","last_updated":"2026-06-08T13:39:25Z","snapshot_observed_at":"2026-08-15T22:29:34.751975Z","submitted_at":"2026-06-08T13:39:25Z","title":"Detecting Differences Is Not Understanding Structure: Large Language Models Fail at Graph Isomorphism","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-06-27T16:28:27.657061Z"},"links":{"cited_paper":"/paper/2412.12456","citing_paper":"/paper/2606.09484"},"observation_digest":"sha256:b0a24964c594e9521c191c4b48e96479dab581e261b93a5a0a6d4c02a1cdba0b","observation_id":"faffc647-47aa-460a-b420-43bc6c91b506","resolution":{"observed_at":"2026-07-03T01:27:31.659343Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.12456/citation-record","integrity":"/paper/2412.12456/integrity","json":"/paper/2412.12456/citation-record.json","paper":"/paper/2412.12456"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.239410Z","title":"Curriculum GNN-LLM alignment for text-attr ibuted graphs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.239410Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:53d3bfef8ba6f7ef14c305979094f99268bf376698a4cf3476e2893599dbc1ae","observation_id":"19bda759-b032-4ba6-8079-3f596f871c45","resolution":{"observed_at":"2026-08-11T14:06:18.239410Z","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":"2026-08-11T14:06:18.244789Z","title":"DP-GPL: Differentially private graph prompt learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.244789Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:2f54c3e2b343cbe73262662cc36fe33ed6d2bdbdf0a55a41a15e40f37ee5a0d5","observation_id":"4ce64d84-2ad4-48fe-a411-996f7a2cd105","resolution":{"observed_at":"2026-08-11T14:06:18.244789Z","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":"2026-08-11T14:06:18.249967Z","title":"Edge prompt tuning for graph neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.249967Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:1aba9c5d2e459d9cd5fb617f2305288f8d9344459b05f7e7f33be548adb76d83","observation_id":"dc56c2d8-8159-4b73-8248-3c36f95c44ea","resolution":{"observed_at":"2026-08-11T14:06:18.249967Z","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":"2026-08-11T14:06:18.255086Z","title":"GFSE: A foundational model for graph structu ral encoding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.255086Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:26e3eeb01cfe0089c639ab802a92160245472c1c5e544a52a9f9b6c2992dda14","observation_id":"9087ff93-cdad-4b33-9f24-67c3add10208","resolution":{"observed_at":"2026-08-11T14:06:18.255086Z","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":"2026-08-11T14:06:18.260063Z","title":"GL-fusion: Rethinking the combination of gr aph neural network and large language model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.260063Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:bac2457a133f2ac7f14613dbfc05fc2b9246416084d07ce5abefa68def07985f","observation_id":"a4827864-1f70-448a-96c6-733f27ab62b1","resolution":{"observed_at":"2026-08-11T14:06:18.260063Z","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":"2026-08-11T14:06:18.264833Z","title":"Graphbridge: Towards arbitrary transfer le arning in GNNs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.264833Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:0a2c830f28823351b6e9b7da5462d3118337bc58c67181c399b798628cd9ac59","observation_id":"6ebfcc7f-f5a9-490a-8c1c-adaf50997369","resolution":{"observed_at":"2026-08-11T14:06:18.264833Z","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":"2026-08-11T14:06:18.269592Z","title":"GraphFM: A generalist graph transformer tha t learns transferable representations across diverse doma ins","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.269592Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:01ae98635e579db0a738eefcdc800f6b5b38b76b9eaea43c6c68aebc2f712020","observation_id":"a78d2f46-78a6-423f-9e26-c6a92e2f8b38","resolution":{"observed_at":"2026-08-11T14:06:18.269592Z","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":"2026-08-11T14:06:18.274878Z","title":"Graphprop: Training the graph foundation mo dels using graph properties","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.274878Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:7c997dd6522b7b195398f0a1040635096920a1d2893244b31efdc9f47592fc90","observation_id":"028827da-ff6f-4e97-ae8c-404aef31a540","resolution":{"observed_at":"2026-08-11T14:06:18.274878Z","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":"2026-08-11T14:06:18.279561Z","title":"Large language models based graph convoluti on for text-attributed networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.279561Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:d92bca7520ef7f7edc7783c416ca8e046c8cb94c137535555b9cebd0d204d449","observation_id":"d934d943-bc61-4669-a1c2-0354d343385a","resolution":{"observed_at":"2026-08-11T14:06:18.279561Z","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":"2026-08-11T14:06:18.284198Z","title":"Link prediction on text attributed graphs: A new benchmark and efficient LM-nested GNN design","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.284198Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:0d25ae6e1e6b711d6c4552eb19197cbc1e32ea6601d1f60f6dbc7705a9b546bc","observation_id":"029689ba-f94a-44e2-a861-345f2527d02f","resolution":{"observed_at":"2026-08-11T14:06:18.284198Z","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":"2026-08-11T14:06:18.288743Z","title":"LLM as GNN: Graph vocabulary learning for gr aph foundation model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.288743Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:3c3dabb6e9c01bd3c949b9e6255839603302aa9b403477684b4243968a7b87fa","observation_id":"da824532-6df1-4265-8345-fb139d832cc7","resolution":{"observed_at":"2026-08-11T14:06:18.288743Z","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":"2026-08-11T14:06:18.293499Z","title":"Low-cost enhancer for text attributed grap h learning via graph alignment","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.293499Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:1ec7a066e2e8655868f2493163342d42d985cefed5348cbb98e209b744b7d215","observation_id":"84059190-0048-4386-bfa4-e5573db2d0af","resolution":{"observed_at":"2026-08-11T14:06:18.293499Z","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":"2026-08-11T14:06:18.298125Z","title":"One model for one graph: A new perspective fo r pretraining with cross-domain graphs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.298125Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:5c4da6888e266c3d0f8cd459877ee4fb5f6d9c88330dda2b48bb5994d122371f","observation_id":"990cf048-1eea-44ab-8c76-cbe74c12e263","resolution":{"observed_at":"2026-08-11T14:06:18.298125Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.869865Z","title":"Text attributed graph node classification u sing sheaf neural networks and large language models","venue":null,"work_id":"56cf87cf-9cf5-4c78-ba82-28d190206073","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.302682Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:70ec895bb594aaf1e6fac8df5e865d9e7e7a1187b73a8638f18da5bfca2b459c","observation_id":"1729f4f8-fdb5-4379-8b0c-6a5e18ceaa84","resolution":{"observed_at":"2026-08-11T14:06:19.874518Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.855001Z","title":"Towards graph foundation models: Learning generalities across graphs via task-trees","venue":null,"work_id":"d0d5f6a8-c357-4a00-b6c9-0a8e89259d98","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.307369Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:4aed87a54e983024220f0c2d6a7c7b406ed844ee9a66de4ced2c5c4a7c2dcccc","observation_id":"1de29da8-2e5a-42f8-8c35-b1ce402fea74","resolution":{"observed_at":"2026-08-11T14:06:19.859782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.841059Z","title":"Lpnl: Scalable link prediction with large langu age models","venue":null,"work_id":"5edc8d45-dea7-4651-96b2-1fae55c6a794","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.311883Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:56e2986b931b25bbfbd41881d1718f670d82400a8479c80f0fc616b55a26fac4","observation_id":"befee49c-70cb-447a-9266-844bc99ecf9a","resolution":{"observed_at":"2026-08-11T14:06:19.845777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.826175Z","title":"Pro tein function prediction via graph kernels","venue":null,"work_id":"47005306-865b-4a14-9e10-671c84540895","year":2005},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.316307Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:e46c96341a9e5b581de9969ea4453ce5637a5dc06e6ed3102dc7b346465b6240","observation_id":"c923b8f3-3f85-4ad7-8d40-9cfe98997043","resolution":{"observed_at":"2026-08-11T14:06:19.831076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.811537Z","title":"Congrat: Self-supe rvised contrastive pre- training for joint graph and text embeddings","venue":null,"work_id":"0c05a46a-e55a-4754-b9bf-d222ebc7a635","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.320901Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:9e5ec4e59ca783b1ed5f04e3885dba01fb8b4b5cfb072b793a3347d38c560f32","observation_id":"fb940322-be69-4845-9a3b-04549f318e7d","resolution":{"observed_at":"2026-08-11T14:06:19.816331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.797179Z","title":"Graphllm: Boosting grap h reasoning ability of large language model","venue":null,"work_id":"8ec8ec6b-4f47-4015-a11e-f59f6ebc422e","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.325363Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:b34ac490238d32c7c946eb29d9e389cf9079d06c35e2d0934fecf8fef0728bd9","observation_id":"d645862b-20a3-4ee3-9ad2-fdcc54313eb8","resolution":{"observed_at":"2026-08-11T14:06:19.801824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.781684Z","title":"Llaga: Large language and graph assistant","venue":null,"work_id":"88d3b75f-0b11-41af-8c35-8b14d707c898","year":null},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.329969Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:17ca6d52cef39dcf6167f9d912e91f3d38957cfc2f7eb48b86b4723bb4429b7b","observation_id":"7dbf215c-19fb-45a3-af03-74e6f99f8751","resolution":{"observed_at":"2026-08-11T14:06:19.787318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.767243Z","title":"Hight: Hierarchical graph tokenization for graph-language align- ment","venue":null,"work_id":"94b93262-a455-4210-a97e-0561efdb1a87","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.334477Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:6544521065ed8ca6c7f7a03e2c27ec4cfae623afda95d171a90a21994c47795a","observation_id":"9562bc2b-01bc-43d1-af4a-b74d922c729e","resolution":{"observed_at":"2026-08-11T14:06:19.772153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.752883Z","title":"Label-free node c lassification on graphs with large language models (llms)","venue":null,"work_id":"7a1cf190-559d-41b9-8aca-82321bb492d0","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.338831Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:217d3b578df74bd2b17e7ee08e779500d3eb0bee22a107abfc150292cfed596d","observation_id":"580e7789-ec6e-48db-a28a-66dac060ba97","resolution":{"observed_at":"2026-08-11T14:06:19.757661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.737897Z","title":"N ode feature extraction by self-supervised multi-scale neighborhood prediction","venue":null,"work_id":"d18162b3-222c-4b91-bfba-7578bacefdde","year":null},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.343333Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:3444684233b7963e202319342aad0fc08c4f367b6e30d3190d4fe75b347c7270","observation_id":"5d84473c-a3b7-4d92-aca3-3c6817f9961c","resolution":{"observed_at":"2026-08-11T14:06:19.742837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.723211Z","title":"Structure-activ ity relationship of mutagenic aromatic and heteroaromatic nitro compounds","venue":null,"work_id":"2605b444-c653-4d26-99c5-89ec2d0cd688","year":1991},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.348124Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:7dc4b931d564f909211640bcb218a27026e2f385745a58f04ae57437dd6222a2","observation_id":"1c360b49-0eae-43ab-92dd-4d2e4b1ddd74","resolution":{"observed_at":"2026-08-11T14:06:19.728273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.708663Z","title":"Distinguishing enzyme s tructures from non-enzymes without alignments","venue":null,"work_id":"326f8caa-b5d5-4907-aaae-750520791400","year":2003},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.352661Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:41836f0e998f19fabcbb7e109d46a0423a35f4a33e20c2889020ff67e79c13e1","observation_id":"ff30a20e-7c44-4716-8ae5-68f2cf198e7b","resolution":{"observed_at":"2026-08-11T14:06:19.713435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.694172Z","title":"Simteg: A frustratingly simple approach improves textual graph learning","venue":null,"work_id":"f8b15ebd-634c-467b-8a3e-59df73073d01","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.356857Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:21a7b8c62ffcd10f2220448392e5c7ae6a61895c0a94218bbbf745f5b9360e4c","observation_id":"100108e1-151b-420a-a574-3886ffcf6c0d","resolution":{"observed_at":"2026-08-11T14:06:19.698965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.680025Z","title":"Universal prompt tuning for graph neural networks","venue":null,"work_id":"7aec3eb3-d9f7-46f2-b7f3-6fbe4a523e46","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.361195Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:d4061479de6e8856445017a59e06d513af892b62abcc4120276038be189267e7","observation_id":"8cd22b3a-99e7-4d0d-900d-0495c9e93eac","resolution":{"observed_at":"2026-08-11T14:06:19.684572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.665318Z","title":"Gaugl lm: Improving graph contrastive learning for text-attribu ted graphs with large language models","venue":null,"work_id":"8a53496b-7f79-45df-beaf-ac1cba586e2a","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.366053Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:d9bb3861ab8ba0c5e19770c7ec2e8be3709aa7ba178c16684c73b508875d52f3","observation_id":"fb80f2af-c504-4038-b073-b997e8cd2b4f","resolution":{"observed_at":"2026-08-11T14:06:19.670279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.651009Z","title":"Ta lk like a graph: Encoding graphs for large language models","venue":null,"work_id":"27ab9826-7c7a-4457-9bf2-8460f8f84e7b","year":null},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.370693Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:b7e2644bc4298f2485816ce9f70922a1d55ac1f049c2dd882e41cc1f0cb99b18","observation_id":"9623275d-fd82-4ed5-8b44-f36823f5674e","resolution":{"observed_at":"2026-08-11T14:06:19.655794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.06893","last_updated":"2018-03-28T18:00:30Z","snapshot_observed_at":"2026-08-14T19:44:21.730838Z","submitted_at":"2018-02-19T22:32:47Z","title":"Learning Word Vectors for 157 Languages","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.06893","snapshot_observed_at":"2026-08-11T14:06:18.375498Z","title":"Learning word vectors for 157 la nguages","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.375498Z"},"links":{"cited_paper":"/paper/1802.06893","citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:70009f0645232f71e47bbfdf6c2af3f000b80f139390168182dd46b88161b28b","observation_id":"81cc1c64-61f5-4fce-8112-a7263eb8d737","resolution":{"observed_at":"2026-08-11T14:06:18.375498Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.636159Z","title":"Gpt4graph: Can large language models understand g raph structured data? an empirical evaluation and benchmarking","venue":null,"work_id":"f2281390-10d6-436f-845c-c53b0525b114","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.380338Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:7f3a4362f5a8305ff17fca67c70e2becc3350468e074e874d96631861e955a7e","observation_id":"9c037679-5993-4739-b97b-30b33ebd4c41","resolution":{"observed_at":"2026-08-11T14:06:19.641041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.621248Z","title":"Harnessing explanations: Llm -to-lm interpreter for enhanced text-attributed graph representation learning","venue":null,"work_id":"d34f6409-a40f-44bf-9b39-236a20c913f2","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.384902Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:bb08907b398a929402739ab413d96fcdb0587d97967eb8209648465bfd69e519","observation_id":"e0333fe3-5450-4e30-a3a3-0ecf3e261d83","resolution":{"observed_at":"2026-08-11T14:06:19.626063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.606861Z","title":"Generalizing graph transformers across diverse g raphs and tasks via pre-training on industrial-scale data, 2024","venue":null,"work_id":"96def7df-b556-4eea-99ca-d61baada2ca5","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.389485Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:74a4e2a4261f8b48d45a89fcac003fdf34fef8b7a5a5931c30f84d272aabb862","observation_id":"61b5aae8-349e-4842-9315-8502b36c691b","resolution":{"observed_at":"2026-08-11T14:06:19.611575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.592226Z","title":"Unigraph : Learning a unified cross-domain foundation model for text- attributed graphs","venue":null,"work_id":"76830bd9-8248-4f8b-9311-33610964c21c","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.394049Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:4a0a0c982ae1a8da2004c5a7eebd553500682c0369d07eff0722d36ba26bfc6f","observation_id":"7b5f78e1-a07a-4152-bc11-14286e75ed1e","resolution":{"observed_at":"2026-08-11T14:06:19.597046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.577108Z","title":"King, Stefan Kramer, and Ashwi n Srinivasan","venue":null,"work_id":"0bb0176e-c353-4bc1-a483-7999145c6487","year":2000},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.398457Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:5ffc2261152df41f65539cf3ad27be1c844431ace4aaa07e0d8a81718a19990e","observation_id":"6dcc99a7-b44a-4248-9807-db3ed204b307","resolution":{"observed_at":"2026-08-11T14:06:19.581743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.562908Z","title":"Graphalign: Pretraining one graph neural network on multiple graphs via feature alignment","venue":null,"work_id":"7a61ab6a-7778-48fb-915f-09d6c9640d9d","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.403189Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:192f7964dd66c334cdc59024827e18bd7eea7c27066facba09768745deb6d278","observation_id":"53256aba-00ea-4b58-964b-b25da6b9e1c5","resolution":{"observed_at":"2026-08-11T14:06:19.567607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.548079Z","title":"Op en graph benchmark: Datasets for machine learning on graphs","venue":null,"work_id":"546ec163-de44-4bb7-8edf-57c7ba841f55","year":2020},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.407601Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:ddc2af7d4b02fcc7b2644270ef2657e53b816d1c945ba28a94c3a171ecbd0e20","observation_id":"e926407e-67d8-407c-ac55-73e0ede26a19","resolution":{"observed_at":"2026-08-11T14:06:19.553037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.533621Z","title":"Scalable and accurate graph reasoning with llm-bas ed multi-agents","venue":null,"work_id":"d15026ee-6ef4-475d-a519-8c5e91f1130c","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.411953Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:02b9580d24fa549e0debf53bf036e6e2f47a7d0dd384797e2dc13bc1c809775b","observation_id":"0232618f-ca6d-4cf3-b6bc-f47a47214d5f","resolution":{"observed_at":"2026-08-11T14:06:19.538436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.519067Z","title":"PRODIGY: Enabling i n-context learning over graphs","venue":null,"work_id":"5e8fd0d4-0e56-4005-84df-74a2f48ad5ac","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.416373Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:23368a05465cc49f67b7ef38e2db72833ef4f39e956a04f36067fd30b140928a","observation_id":"8641fe96-fae4-4be7-b4b1-8a3e88ae24df","resolution":{"observed_at":"2026-08-11T14:06:19.523715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.504600Z","title":"Can gnn be good adapter for ll ms? 2024","venue":null,"work_id":"bf383dc0-8f69-40da-9511-01176d189872","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.420971Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:9b5c8e7cae5b718b33a0889f796800adaf1b350213cde6f18b111a7f54f7f7e9","observation_id":"d2f496c3-2441-4547-b0e7-958d0cf9af79","resolution":{"observed_at":"2026-08-11T14:06:19.508973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.490094Z","title":"Ragraph: A general retrieval-augmented graph learning framework","venue":null,"work_id":"4ed3a645-9f8a-4f83-80ca-2b12481662df","year":null},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.425464Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:889dd9f337cee6b10b2b02afc29d92c3ac77e27ce820feb2ad6f5539664ae628","observation_id":"0f92b23f-4b8d-4d8e-a3fd-f5ddbf23181e","resolution":{"observed_at":"2026-08-11T14:06:19.495139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.475801Z","title":"Patton: Language model pretraining on text-rich networks","venue":null,"work_id":"768e0d60-0f9f-4d7e-8224-b01285864faa","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.430308Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:11ce832d22d6b89cce0c1567222c3a93c2dfbeccbb9fac88de45516eda4b701d","observation_id":"b1236a57-1998-4851-8d1e-2b4fa2a74edd","resolution":{"observed_at":"2026-08-11T14:06:19.480561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.461156Z","title":"Gofa: A generative o ne-for-all model for joint graph language modeling","venue":null,"work_id":"6d4d7577-3a71-4505-946d-2ed2daa1ed60","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.435037Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:65f9898f70196898508f9725d64a01338047d08678f69d85a6a251a185c90195","observation_id":"fe6f252a-7a33-4e3b-9de3-03f8ae65762e","resolution":{"observed_at":"2026-08-11T14:06:19.466017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.446623Z","title":"Graphs over time: densification laws, shrinking diameters a nd possible explanations","venue":null,"work_id":"c23a11bf-19c0-40bd-9dbe-d079d2ea5a51","year":2005},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.439782Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:d548eae741b4b7ffb122d2f521d6c7037bb7c226c09f3a6e86fdd9515573f15d","observation_id":"ff9e3eb7-8205-4d94-9983-465dc0548919","resolution":{"observed_at":"2026-08-11T14:06:19.451603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.431488Z","title":"Snap datasets: Stanfor d large network dataset collection","venue":null,"work_id":"d70cafd8-c9d1-4220-b8ee-082c64d10544","year":2014},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.444543Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:61d8b1fc47491a2530919c723ae5019ef3032a00e00a2de53946c7d9edfe8ea4","observation_id":"60a91541-6ffd-4e0e-84bc-6824d1daee4c","resolution":{"observed_at":"2026-08-11T14:06:19.436548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.02846","last_updated":"2021-09-07T03:59:22Z","snapshot_observed_at":"2026-08-13T18:16:02.359532Z","submitted_at":"2021-09-07T03:59:22Z","title":"Datasets: A Community Library for Natural Language Processing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.02846","snapshot_observed_at":"2026-08-11T14:06:18.449062Z","title":"Datasets: A community lib rary for natural language processing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.449062Z"},"links":{"cited_paper":"/paper/2109.02846","citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:dbcf900b08a6dd2d2fc140f099727a180ad621aad07b155dce7d28bd52e49bc4","observation_id":"6652db65-ac99-45f0-b09e-1caa247b29ac","resolution":{"observed_at":"2026-08-11T14:06:18.449062Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.416739Z","title":"Finemo ltex: Towards fine-grained molecular graph-text pre-train ing","venue":null,"work_id":"bc4720c4-fda2-4b23-b5f9-54c4a8c3c5b8","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.453905Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:4d35539e8e98870de2453f54bbedf193b5bdb8b09d85bed0a21c8787133f9846","observation_id":"0cd416c5-0a41-4687-b2ee-08f2b3de52d8","resolution":{"observed_at":"2026-08-11T14:06:19.421355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.402175Z","title":"Grenade: Graph- centric language model for self-supervised representatio n learning on text-attributed graphs","venue":null,"work_id":"2a6deafa-5727-48b3-a0ff-b626e75a4b76","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.458486Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:d7864bc74742299c108017317435c486e51bde96ab139928fe88a5246d970aac","observation_id":"fb520cc7-61c0-4119-a256-8e177978df33","resolution":{"observed_at":"2026-08-11T14:06:19.406965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.387148Z","title":"Zerog: Investigating cross-dataset zero-shot transfer ability in graphs","venue":null,"work_id":"c1e6b3d2-9bda-4dae-b361-6bf6c1b60891","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.463065Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:fb2e616675f191ddf26bcdb1e4e041c9266acf2f15a54d65ecfcad420347748f","observation_id":"358f5b4e-7413-4115-861d-43fc3f0fbd20","resolution":{"observed_at":"2026-08-11T14:06:19.391923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.372616Z","title":"Toloker Graph: Interaction of Crowd Annotators","venue":null,"work_id":"77a56521-af2e-440a-a096-612d0c63d968","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.467639Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:317f98816719eea9e3e31852f32f27f50207c308ebc11f7669a8bc4a18fbb804","observation_id":"3c22e376-3295-4e9f-a1be-52ad2a788c1a","resolution":{"observed_at":"2026-08-11T14:06:19.377343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.358387Z","title":"Link predict ion on textual edge graphs, 2024","venue":null,"work_id":"e750a643-a70a-47ce-a8eb-98f8c1139c6a","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.471985Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:6c695cfdb66c7e0d31a74ce08072535b4ca0c1495cd252e03dbfa6f7725e54c4","observation_id":"289873d0-9b54-4d36-9fcf-058129bb09be","resolution":{"observed_at":"2026-08-11T14:06:19.363133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.344030Z","title":"One for all: Towards tra ining one graph model for all classification tasks","venue":null,"work_id":"e05f69ce-4ea6-43c8-8e15-4933119b088d","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.476598Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:25b6feee0e4292b3e37f3e8876d733680285562e52fcdf68b53ac1c4aab5785e","observation_id":"9dd40358-5731-44c9-860c-9aec84d505bb","resolution":{"observed_at":"2026-08-11T14:06:19.348591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.329699Z","title":"Gr aphprompt: Unifying pre-training and downstream tasks for graph neural networks","venue":null,"work_id":"d091806d-7329-4b2f-9b0e-960a1001c4c5","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.480800Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:c7d042b030901987a04c0ed7d419220c64d0d506aa359dca07ebda37e34adf3a","observation_id":"9a11f64d-60f3-4882-a1d1-7f114670407b","resolution":{"observed_at":"2026-08-11T14:06:19.334478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.315145Z","title":null,"venue":null,"work_id":"d9edcf72-921d-45f3-bb70-91857742166e","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.485043Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:0d69099ad29f255333b9c4d4b926c22258f5dd538d259b7533b0d82d7a267ab2","observation_id":"03f6ec00-93cf-42f5-85f3-fabfeb62dafa","resolution":{"observed_at":"2026-08-11T14:06:19.320047Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.300087Z","title":"Ioannidis, Shen Wang, D a Zheng, Soji Adeshina, Jun Ma, Han Zhao, Christos Faloutsos , and George Karypis","venue":null,"work_id":"679c5c49-b5db-47d3-b9e0-9d742cebb93a","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.489501Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:b8c1e5043a94041e41c451add8d3f5e7c357db524b21c336c737433695a93b48","observation_id":"a6cd85c3-e704-4469-9616-378f989799c1","resolution":{"observed_at":"2026-08-11T14:06:19.304776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.285116Z","title":"Tagexplainer: Narrating graph explanati ons for text-attributed graph learning models","venue":null,"work_id":"1f6d49c7-8da8-4e3a-94df-38bd35b6375f","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.493925Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:816e26e30a0c8770e6d24c0381410cbc81216c29eb1d408d574a499d63310d27","observation_id":"c2e038e5-d76d-4ae2-9af6-65e36e3c5727","resolution":{"observed_at":"2026-08-11T14:06:19.289983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.269846Z","title":"Distilling large language models for text-attributed graph learning","venue":null,"work_id":"22c1988c-a7eb-4b40-8fe9-5b4c946ed3fd","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.498372Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:78456dad8d3c38daffb6577ac4fe3648081bdd4bcb8d5531fc798d8f9e95b493","observation_id":"54a9e1be-f05b-4d02-b43b-729a8a20692f","resolution":{"observed_at":"2026-08-11T14:06:19.274555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.254698Z","title":"L et your graph do the talking: Encoding structured data for llms","venue":null,"work_id":"291fa5fc-05f1-4b93-8adb-81755aecd584","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.502964Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:74350e538010ceabe10159c57a4da26e080b0ac06060588cce64070d915ffa0f","observation_id":"e22883a4-5b82-4cb7-a1ef-19ce5dab1600","resolution":{"observed_at":"2026-08-11T14:06:19.259772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.239946Z","title":"Disent angled representation learning with large language models for text-attributed graphs","venue":null,"work_id":"de02db2e-d82e-4a71-a2ea-6c4f5b749fc2","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.507335Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:f9f0674050adefa26d66980c19676d2a62c2facac0fe2b215e34bfffaacd6251","observation_id":"e66377d7-ef16-4e77-a154-82b9e906c3d0","resolution":{"observed_at":"2026-08-11T14:06:19.244809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.225050Z","title":"Iam graph database repos itory for graph based pattern recognition and machine learn ing","venue":null,"work_id":"45f84a61-b6f1-4cfe-8b80-172f762b767a","year":2008},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.512300Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:981b82ccf2748cede69f98babf8b7923ba292d06768098a343f7ab5c9787db38","observation_id":"1e81351f-3090-484a-a5ee-114097d41975","resolution":{"observed_at":"2026-08-11T14:06:19.230052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.210564Z","title":"Unleashing the potential of text-attributed graphs: Automatic relation decomposition via large language models","venue":null,"work_id":"15725f04-23d0-4a74-9ce2-75fd8d08cbc3","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.516746Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:05f236aba2691d08a5401615d31db340aae7509165e646df2a2f20215e2f04eb","observation_id":"8d309fe2-803e-4534-9f36-b7feb4cf8688","resolution":{"observed_at":"2026-08-11T14:06:19.215249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.05868","last_updated":"2019-06-18T13:15:39Z","snapshot_observed_at":"2026-08-14T17:59:20.424546Z","submitted_at":"2018-11-14T15:53:19Z","title":"Pitfalls of Graph Neural Network Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.05868","snapshot_observed_at":"2026-08-11T14:06:18.521242Z","title":"Pitfalls of graph neural netw ork evaluation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.521242Z"},"links":{"cited_paper":"/paper/1811.05868","citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:441f9d8fb00c1afc610a3bd93583727470856d5a253bfe5a7b9d8ffe11dfbb41","observation_id":"8e695d04-de14-4a02-9afa-2314e794a34f","resolution":{"observed_at":"2026-08-11T14:06:18.521242Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.196045Z","title":"A multi-view mixture-of-experts based on language and grap hs for molecular properties prediction","venue":null,"work_id":"1b4787a9-a42f-43a8-ae20-36afb5abc39d","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.526153Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:8ba023b8712464df70adba347fc3ab9068a1316dee0488afc785d27e6dfdc0a2","observation_id":"587e100e-6f9e-4800-bc6a-f4a1c5079c9a","resolution":{"observed_at":"2026-08-11T14:06:19.201044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.179514Z","title":"Gppt: Graph pre-training and prompt tuning to generali ze graph neural networks","venue":null,"work_id":"3a7df373-1077-44e3-b72c-693fd51bb444","year":2022},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.530639Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:0cba47f3e2c1f3a2ce1ab7ea6cc361c867f288cc793705846a878d3c438544c7","observation_id":"45fcb521-e743-4e71-a734-4b28767a261a","resolution":{"observed_at":"2026-08-11T14:06:19.184558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.164612Z","title":"All in one: Multi-task prompting for graph neural networks","venue":null,"work_id":"bf5b7f17-b540-4d49-b23f-26e40664e2c0","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.534975Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:2629a10a3e9b6badd2453867b1baacd097d52324c89b9efd2f3abc0b0c292132","observation_id":"6b944880-bfde-42eb-be36-51bf9246ff62","resolution":{"observed_at":"2026-08-11T14:06:19.169576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.149490Z","title":"Spline-fitting with a genetic algorithm: A method for develo ping classification structure- activity relationships","venue":null,"work_id":"6e1144ed-f308-4f0d-8142-48c9cc519374","year":1906},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.539526Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:4157ea557904ec04ff2473c1313ef6a2f95e2de975827ac097fe66bffb0d3bf2","observation_id":"d3324ee2-42f8-43a5-b7cf-4876461ae182","resolution":{"observed_at":"2026-08-11T14:06:19.154439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.134513Z","title":"Musegraph: Graph-oriented instruction tuning of large language models for generic graph mining","venue":null,"work_id":"9dba65a6-f5df-480a-bfa0-8072d1442b82","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.544246Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:d3ef94f90a8babb05df186dfbee398aed2660c6c1a65f79c3c056d1df5a6e039","observation_id":"97515024-a7a0-486c-99d4-f79550e5d35b","resolution":{"observed_at":"2026-08-11T14:06:19.139393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.118987Z","title":"Walklm: A uniform language model fine-tuning framework for attributed graph embedding","venue":null,"work_id":"bf7321a3-336a-4946-9b55-5f9dd5e666b0","year":null},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.548888Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:8b71fba210b20793134345f887e20d7b16d544d9f41bf6726ef75f459a05a1bd","observation_id":"87e3fea5-facc-4423-97a1-77a1ab4de40b","resolution":{"observed_at":"2026-08-11T14:06:19.124069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.103929Z","title":"Graphgpt: Graph instructi on tuning for large language models","venue":null,"work_id":"d03085aa-0bbf-4f1b-9e3d-fe94bee9ef82","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.553924Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:576f2715767fa45060158c4494936fe611b9d8d3b42428a54b2f9d0b3c4bfb54","observation_id":"c6b07a46-9a87-41cc-9f8c-96376aad9f53","resolution":{"observed_at":"2026-08-11T14:06:19.108825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.089655Z","title":"Higpt: Heterogeneous graph language m odel","venue":null,"work_id":"60d84dda-615b-4a12-aab1-863a5ee4a124","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.558353Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:df1b518ea40689e34abc1581f0b5ce8bacc811007097acee3c00c1e735dcc528","observation_id":"7a529316-cd68-4413-9e48-b1e1ac849dbc","resolution":{"observed_at":"2026-08-11T14:06:19.094162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.074200Z","title":"Compariso n of descriptor spaces for chemical compound retrieval and c lassification","venue":null,"work_id":"a81681ed-b3fe-4223-9202-1a94312cf529","year":2008},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.562967Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:cc165c9245cd8899bb758b92d7e617f60b45b4714b661f854b7d4034c6e7715d","observation_id":"be1c1af5-80b6-4f06-86e5-36941c4ec3d0","resolution":{"observed_at":"2026-08-11T14:06:19.079465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.060025Z","title":"Can language models solve graph problems in natural language? 2024","venue":null,"work_id":"09a8968a-f023-49ab-b4a1-d754e2b664c2","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.567981Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:d98dee2ce5c774938d960ca20698283fbe98471a17485d6e58cf54c5506cb8ed","observation_id":"5c1ff46d-b8b5-487c-922b-b0e53dc4cb28","resolution":{"observed_at":"2026-08-11T14:06:19.064615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.045232Z","title":"Instructgraph: Boosting large language m odels via graph-centric instruction tuning and preference alignment","venue":null,"work_id":"53baf4e4-0189-4978-b575-ba56ed1dc175","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.572673Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:057d3a2256c30da63acab04ad298b713d90a67b80ed441bebfbea05b5f03b6d0","observation_id":"69cffa0b-f015-4d47-8483-3743fd079abc","resolution":{"observed_at":"2026-08-11T14:06:19.050152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.030011Z","title":"Towards graph foundation mode ls: The perspective of zero-shot reasoning on knowledge gra phs","venue":null,"work_id":"6e67e2a3-ce49-418c-8bda-6d331fbdec5f","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.577260Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:f45340ded055e85ea0a9ef716acc3f94f92ebe695b15af5ca46e5fdd0c409a3f","observation_id":"42ab68b3-552d-4dc5-b42a-42a2f98fbca1","resolution":{"observed_at":"2026-08-11T14:06:19.035010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.015306Z","title":"Microsoft academic grap h: When experts are not enough","venue":null,"work_id":"90cf4854-30d6-4661-9a0c-ad59d02d3687","year":2020},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.581752Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:2d1310eb5846420e045586a01d37c877f52644f996c8d54d8620555e9ef10f32","observation_id":"51c7ae3f-70d8-4f84-8bea-d57965ffc436","resolution":{"observed_at":"2026-08-11T14:06:19.020102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:19.000689Z","title":"Learning graph quantized tokenizers for transformers","venue":null,"work_id":"aeea0b70-1304-4a0a-ae91-5cebec3fd265","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.586549Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:0374f07993dfd68d4b1b42244039f037c72ee222d9f997dadc04112474eef038","observation_id":"e95fe753-fb6a-4edb-a42c-98c9d17f2bb7","resolution":{"observed_at":"2026-08-11T14:06:19.005431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.985406Z","title":"Augmenting low-resource text classification with graph-grounded pre-training and promp ting","venue":null,"work_id":"018b77f8-20b1-4561-b4dc-bd09183c3d6b","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.591100Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:697fef24234f3748523bcedb88dc5e888d1c0b0b965de1d7a08b1e3e8d8d4d47","observation_id":"d05c8c1e-3698-441d-a4bb-64335d7a9355","resolution":{"observed_at":"2026-08-11T14:06:18.990314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.970820Z","title":"Anygraph: Graph foundatio n model in the wild","venue":null,"work_id":"e313a6e2-4a1f-44e5-b363-85a5f673fdd2","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.595716Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:dad29c9c64f4fbaa11a69f30379c5441e4853674a35ce3c9dc2a821ed7ef146f","observation_id":"824ffbae-c9b0-4f2c-a592-5491bec08122","resolution":{"observed_at":"2026-08-11T14:06:18.975463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.956020Z","title":"Opengraph: Towar ds open graph foundation models","venue":null,"work_id":"7dda985d-22b8-4115-9dc7-f000cfde2792","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.600148Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:7a3b4dcebb9232f630c2af6a6fccd28e85fbcfb3be9b14e02e9b466423c46df3","observation_id":"17241a5b-f3a4-4cc4-9a09-b2380a1f0d05","resolution":{"observed_at":"2026-08-11T14:06:18.960848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.941143Z","title":"Ioann idis, Xiang Song, Qing Ping, Sheng Wang, Carl Yang, Yi Xu, Bel inda Zeng, and Trishul Chilimbi","venue":null,"work_id":"fbc06d9b-f18a-4cbe-8f7c-68867819ae38","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.604512Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:6e7d1a43572f21f7c81d9dafe626e18954d27dd11d705f9a47b7ca4ed020a693","observation_id":"d0d6d0be-e5cb-443a-8f04-e72bcf95703f","resolution":{"observed_at":"2026-08-11T14:06:18.946017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.926698Z","title":"Language models are graph learners","venue":null,"work_id":"86a7fe4f-5618-4fdc-acc0-ce5abe4f6c59","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.609069Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:15b5122f633872ed5665ac5da606bfc1a2de74b9346d2d00d7ee7686d0d580d7","observation_id":"cb780988-b22a-495a-b0fe-e16d73fa838d","resolution":{"observed_at":"2026-08-11T14:06:18.931464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.910472Z","title":"Deep graph kernel s","venue":null,"work_id":"fecc918a-d474-4048-bef6-d97b099c3e29","year":2015},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.613578Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:7b6866ee9ed575ef385f498d139cc570989662cdc73e8f2db1a9da97fbecac05","observation_id":"7bda5377-f09e-477b-a8de-e4fa78cb249a","resolution":{"observed_at":"2026-08-11T14:06:18.915136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.896254Z","title":"Cohen, and Ruslan Salakhutdino v","venue":null,"work_id":"1420e6c4-609e-4fdd-8544-f3fa40f396eb","year":2016},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.617925Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:92cb7e6ef95ed2be8a92d038fd21e822948e04a9492a80881b61024a2d927a3d","observation_id":"a6c5d1d9-5861-461c-9c0a-6c560778061b","resolution":{"observed_at":"2026-08-11T14:06:18.900908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.881693Z","title":"Language is all a graph needs","venue":null,"work_id":"6103e813-9d6b-4ac2-a1e3-e65f41aa71cb","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.622467Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:0b5f8337934f56efdee1a287fb3ba8e0563169f8210ffedc0c4cce55803e7410","observation_id":"7255c11e-6893-41f4-a73d-7d164bfab615","resolution":{"observed_at":"2026-08-11T14:06:18.886382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.866217Z","title":"M ultigprompt for multi-task pre-training and prompting on g raphs","venue":null,"work_id":"cb86a459-8479-4d45-b266-575fa1e523bb","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.626809Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:e66154901c28ea5ee59c0919e4a44c03bb06846e9bf64c313d70817a5332a8e4","observation_id":"b37e40d6-e36a-412c-b68a-35671328151f","resolution":{"observed_at":"2026-08-11T14:06:18.871237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.851279Z","title":"Graphtra nslator: Aligning graph model to large language model for open-ended tasks","venue":null,"work_id":"d474b8d9-0fff-4b98-bb03-4ea3e2f3185f","year":null},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.631044Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:9dd28194cfa7ec4c9d932a5fa83b7e5b522bb9a84137e04ae3fa6ba1854628ed","observation_id":"2e5187af-e8fd-4855-901b-21db041d44d2","resolution":{"observed_at":"2026-08-11T14:06:18.856390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.835710Z","title":"Taga: Text-attributed graph self-supervised learning b y synergizing graph and text mutual transformations","venue":null,"work_id":"b73a2c51-cfca-4d12-90d1-f79b0b950d5a","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.635497Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:c3a07126351f05d62ba01ee83644b503527ca04052111e0492168604d3854157","observation_id":"1b0539e5-5046-495a-be5d-c9c63adbfc50","resolution":{"observed_at":"2026-08-11T14:06:18.841010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.818806Z","title":"Graphany: A foundat ion model for node classification on any graph","venue":null,"work_id":"ba2566a4-2fa3-4a65-9e2d-45f82bc325ad","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.639878Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:e0d32f33fa2fa3af994517f885bfad297944fc595fe5fb08c94676637a06bb0d","observation_id":"327ebd68-1969-4d99-80d1-dc80aaa3711c","resolution":{"observed_at":"2026-08-11T14:06:18.824574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.802928Z","title":"Learning on large-scale text-at tributed graphs via variational inference","venue":null,"work_id":"35dabe0b-d133-4b5c-a56a-7d12da2a480c","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.643977Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:25dafc9a31c1bffb79264bc482e575be46b1ab500fa664e17fd958b155b7ee24","observation_id":"40c9dd14-c00c-4630-b7dc-5a1c5adcc4ec","resolution":{"observed_at":"2026-08-11T14:06:18.807923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.787402Z","title":"Graphtext: Gra ph reasoning in text space","venue":null,"work_id":"92ccc031-b9f2-4d27-84f1-3890e38f4b4f","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.648064Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:cec6f5056e994c15883f3ba79d0f8791046d4d9bb68ad01a561b663ecfab842f","observation_id":"a5fab213-6a31-4d99-97f8-e3af7e56965f","resolution":{"observed_at":"2026-08-11T14:06:18.792306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.771674Z","title":"Ioannidis, Danai Kout ra, and Christos Faloutsos","venue":null,"work_id":"94f19a26-3aee-433d-94de-0dd4653dff38","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.652379Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:2a7ab5bd141882d9a732d0cc71bd48b516714d9795ea9e28cb9ff186034b08da","observation_id":"a092c196-827a-4e99-8b55-ee2e5e5794a9","resolution":{"observed_at":"2026-08-11T14:06:18.776758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.755995Z","title":"Effici ent tuning and inference for large language models on textua l graphs","venue":null,"work_id":"cb50b67c-6be8-45fb-a247-ffe148733d88","year":2024},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.657017Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:e0420413aa7867ae92f08ecb01df1ca435b877a6e1d9a833528cf54bd090e480","observation_id":"b81a9bb5-7b9c-44eb-bb5f-dce91c808824","resolution":{"observed_at":"2026-08-11T14:06:18.761163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:06:18.738937Z","title":"Pre training language models with text-attributed heterogene ous graphs","venue":null,"work_id":"3c0c7e46-e3e7-4ee7-9906-cc93076ff5af","year":2023},"citing_paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-11T14:06:18.661273Z"},"links":{"citing_paper":"/paper/2412.12456"},"observation_digest":"sha256:f9ecc06be27a9df8f47caab4568d3653b4a6b72c72db55e7517bc70fc78b7292","observation_id":"47ed0e2d-6239-419c-9e83-ee83b23e97e2","resolution":{"observed_at":"2026-08-11T14:06:18.745622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.12456","last_updated":"2024-12-17T01:41:17Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T15:13:48.353715Z","submitted_at":"2024-12-17T01:41:17Z","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks"},"reference_resolution":{"displayed":93,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":76},"total_outbound_references":93},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 93 of 93 outbound references and 4 inbound Pith citation observations for arXiv:2412.12456."}