{"as_of":"2026-08-07T23:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7e657d7e5dd6115bab26d285c792f6de6e452266bb7ec278610c30abc1f996d3","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:12:27.928253Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T19:16:15.616715Z","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":"2026-07-01T14:55:47.461885Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"cited_work":{"arxiv_id":"2507.09132","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.09132","snapshot_observed_at":"2026-07-01T14:55:47.461885Z","title":"Heterogeneous graph prompt learning via adap- tive weight pruning.arXiv preprint arXiv:2507.09132","venue":null,"work_id":"00067153-2200-4aae-8198-d8148fa14033","year":2025},"citing_paper":{"arxiv_id":"2605.15888","last_updated":"2026-06-05T02:17:47Z","snapshot_observed_at":"2026-08-02T15:57:41.366470Z","submitted_at":"2026-05-15T12:19:18Z","title":"CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-20T20:16:26.671005Z"},"links":{"cited_paper":"/paper/2507.09132","citing_paper":"/paper/2605.15888"},"observation_digest":"sha256:a26334d1a728b9afdce93515592dfd2f1859f89ddb5e0121d68f397ce2e07cf3","observation_id":"e9792199-862a-46af-a4af-c4c622aea379","resolution":{"observed_at":"2026-05-20T20:18:59.773246Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"cited_work":{"arxiv_id":"2507.09132","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.09132","snapshot_observed_at":"2026-07-01T14:55:47.461885Z","title":"Heterogeneous graph prompt learning via adap- tive weight pruning.arXiv preprint arXiv:2507.09132","venue":null,"work_id":"00067153-2200-4aae-8198-d8148fa14033","year":2025},"citing_paper":{"arxiv_id":"2605.15888","last_updated":"2026-06-05T02:17:47Z","snapshot_observed_at":"2026-08-02T15:57:41.366470Z","submitted_at":"2026-05-15T12:19:18Z","title":"CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-30T19:16:15.616715Z"},"links":{"cited_paper":"/paper/2507.09132","citing_paper":"/paper/2605.15888"},"observation_digest":"sha256:039ddff8952611d9c43ab8c921946cf9986ba4858df83b6fe97f9e36afe5e856","observation_id":"e1865b20-c6df-4498-bb79-e2003cede353","resolution":{"observed_at":"2026-07-01T14:55:47.463462Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.09132/citation-record","integrity":"/paper/2507.09132/integrity","json":"/paper/2507.09132/citation-record.json","paper":"/paper/2507.09132"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:12:29.973917Z","title":"A survey of graph neural network based recommendation in social networks,","venue":null,"work_id":"86d11c30-6afa-4f35-8695-fdb04a03dcd7","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.211848Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:b9186ec78dd36db679d73bac858d9cc3414b44fc4553e2ee95b94592efa742e8","observation_id":"22d175e2-cdbb-4bd2-904e-84a2c6ea92fe","resolution":{"observed_at":"2026-08-06T18:12:29.982435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.949019Z","title":"Multi-behavior graph neural networks for recommender system,","venue":null,"work_id":"775b2010-1c89-4f01-9e96-44221d1efd25","year":2022},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.241346Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:cfe3bc7ca9e66b0f910170337c8bf01d6f1de7233c99b727efa6c2ec8b6b657e","observation_id":"55f5dc42-12b0-4842-a177-0ba6919473bc","resolution":{"observed_at":"2026-08-06T18:12:29.961771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.919807Z","title":"Deeprank-gnn: a graph neural network framework to learn patterns in protein–protein interfaces,","venue":null,"work_id":"6e0fa363-1607-4ff2-9a54-11675a2c5ec1","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.273469Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:4a809d2d9c1bccbf33657891e4bb708dc96cf4d00a01138f2a9218214e52a28d","observation_id":"c20329d9-8f11-401b-9ede-8f5930513aab","resolution":{"observed_at":"2026-08-06T18:12:29.938415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.872195Z","title":"Illuminati: Towards explaining graph neural networks for cybersecurity analysis,","venue":null,"work_id":"939f367e-95bc-44ec-8fba-432baf5d95b2","year":2022},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.309536Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:c50c7cca52db38de2cd8fa09c1b233a5bf43bb80785577dd5fb08a1800b776dd","observation_id":"70e04664-0509-437f-9bef-37bfde93833b","resolution":{"observed_at":"2026-08-06T18:12:29.891412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.848836Z","title":"A comprehensive survey on graph neural networks,","venue":null,"work_id":"8f8c8c50-0095-4020-8784-0120aa890d92","year":2020},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.332174Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:07de6e0ba49c1740ab31cb3eb90e9283cfca2276dab4d8c813b395e7b9490409","observation_id":"34a861e6-1005-41f3-822f-8f62cbf0ba4d","resolution":{"observed_at":"2026-08-06T18:12:29.860208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.821883Z","title":"Smoothing adversarial training for gnn,","venue":null,"work_id":"5164cc08-fa98-40b0-b0b4-d902cf98a1a8","year":2020},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.359370Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:1ddfdfa4a0ad4622002f619f5ab4e5b3b351a2a7822a2268a88674b5dd7cd8d4","observation_id":"b86714fb-7c4a-4f2a-be69-38a95b840e0c","resolution":{"observed_at":"2026-08-06T18:12:29.831966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.809099Z","title":"Cost-sensitive gnn-based imbalanced learning for mobile social network fraud detection,","venue":null,"work_id":"c16aa599-e409-4932-b3a6-e12d35a3a65f","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.392629Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:4f5548ab5f8b6f7e6b2c004eb151874797d1b0a990355597ed3319aa972c6589","observation_id":"e5ed0954-c2a7-4e15-b408-1622b4d1ea98","resolution":{"observed_at":"2026-08-06T18:12:29.813593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.774931Z","title":"Label-dependent graph neural network,","venue":null,"work_id":"624be74f-89fd-4e9f-aee8-faf3e5ae3227","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.421720Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:561fe0edf5c6167e4fe879699ac68b64ee863c4fb4d6909806e72b056538f1c0","observation_id":"dfe138cf-2370-4553-b715-58f5ce59a84b","resolution":{"observed_at":"2026-08-06T18:12:29.792788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.752284Z","title":"Wiener graph deconvolutional network improves graph self-supervised learning,","venue":null,"work_id":"643bacbf-c932-44bd-8c21-c258f3758fc8","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.438800Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:9128e6942f826764d8bcbd579c6b798678521c4fee4099f4121b7e765ee4fb4a","observation_id":"a5076e60-ca9a-46b7-a293-50d3d8fdb1de","resolution":{"observed_at":"2026-08-06T18:12:29.766007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.724730Z","title":"Pre-training on large-scale heterogeneous graph,","venue":null,"work_id":"85e41234-04ad-48d9-8323-5d39cbe0397a","year":2021},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.451641Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:553449622ba48582c9baac55accdb94d1e7b8ea1b4761d80a82d00919d70e3db","observation_id":"7410ddad-ff25-448a-b267-606da4303a16","resolution":{"observed_at":"2026-08-06T18:12:29.737091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.691569Z","title":"Node similarity preserving graph convolutional networks,","venue":null,"work_id":"210f5367-359f-4aca-b249-ce2712ccd242","year":2021},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.464364Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:b532ad994083f3bcc9f3303dc43b641feeec7c8d077d7f1e618433e62a592940","observation_id":"de15556d-89da-44b3-add8-0ca2fac4836b","resolution":{"observed_at":"2026-08-06T18:12:29.708179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.666834Z","title":"Generative pretraining from pixels,","venue":null,"work_id":"b14314f4-7d61-42d1-af68-8efbd867afde","year":2020},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.479150Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:4929acd7d042a0897c32de3b6d5fd2fe4198082286c6a0151be490d1e6453701","observation_id":"5eccd5c6-5fae-4987-93d1-c89d42e82a7c","resolution":{"observed_at":"2026-08-06T18:12:29.677134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.632718Z","title":"Unified language model pre-training for natural language understanding and generation,","venue":null,"work_id":"02e7c19f-760f-4ee9-92d2-80af9b7a4350","year":2019},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.513130Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:e45f3eba769c54d67c44177073ce437387cedee21b7a01cd9837735b7bbfd525","observation_id":"1ff3ca20-9ede-4e9b-9443-d8c1d51ff391","resolution":{"observed_at":"2026-08-06T18:12:29.645987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.599148Z","title":"Language models are few-shot learners,","venue":null,"work_id":"148f9814-a4bc-4ce5-80ce-02b3cc6f5fbf","year":1901},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.544509Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:e3940a072f57dc9cd7c954eb8c48c43b904d8a9611b035ac033e133da2165764","observation_id":"1cf92e51-37d4-4fab-8bf8-74a2cc599c2d","resolution":{"observed_at":"2026-08-06T18:12:29.621551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.07602","last_updated":"2022-03-20T15:13:08Z","snapshot_observed_at":"2026-08-03T22:14:53.516423Z","submitted_at":"2021-10-14T17:58:47Z","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.07602","snapshot_observed_at":"2026-08-06T18:12:26.565697Z","title":"P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.565697Z"},"links":{"cited_paper":"/paper/2110.07602","citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:1f72cd4f78596afa3e79aeec9afad8c5a7b10d8e2f2b54e093fa93512fdf2c8a","observation_id":"23628d81-c06b-4c72-8ecc-2009a00ec602","resolution":{"observed_at":"2026-08-06T18:12:26.565697Z","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":"2026-08-06T18:12:29.567148Z","title":"Gppt: Graph pre- training and prompt tuning to generalize graph neural networks,","venue":null,"work_id":"4baccf26-4e79-4708-92b5-3aea7cfd5122","year":2022},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.578998Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:d20992df956d01b3ba6ffda8c3cae99d4710000d0d28e8c439c705f86986cd42","observation_id":"71df6824-8edd-4325-80b7-882e5f5a6a9e","resolution":{"observed_at":"2026-08-06T18:12:29.577735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.532278Z","title":"Graphprompt: Unifying pre- training and downstream tasks for graph neural networks,","venue":null,"work_id":"73f94cac-e08a-44b2-b346-d37a3de700af","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.608488Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:aceb3ebba38917c522917c4ff9cccc22740686db5f84b6487bd7dc3572dfc818","observation_id":"7cfddd6d-892b-4367-8975-999322b84822","resolution":{"observed_at":"2026-08-06T18:12:29.546623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.488413Z","title":"Domain adaptation via prompt learning,","venue":null,"work_id":"2a137007-3767-4424-8714-3eb830a4b427","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.642286Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:43f78bf930dc2032a0356c0b3e48912def44a4ddd8a1f6e93f51da768b59ae49","observation_id":"92688ab2-238f-4b1f-8af0-ec01512344b6","resolution":{"observed_at":"2026-08-06T18:12:29.509874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.447137Z","title":"Hgprompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning,","venue":null,"work_id":"a43a81ae-8ecc-4dff-b55a-47094a386653","year":2024},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.670174Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:598249ace87d634a2734844a17950c8ac1f9758da7bb86d86ea1c8c9005e233b","observation_id":"a7c8f761-2c10-4a21-82b0-5e1b15e4d1dd","resolution":{"observed_at":"2026-08-06T18:12:29.457028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.15318","last_updated":"2025-02-04T20:15:39Z","snapshot_observed_at":"2026-08-03T15:20:27.706605Z","submitted_at":"2023-10-23T19:35:57Z","title":"HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks","version":4},"cited_work":{"arxiv_id":"2310.15318","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.15318","snapshot_observed_at":"2026-08-06T18:12:28.143904Z","title":"HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks","venue":"cs.LG","work_id":"97b8589d-d3d6-459f-8053-e43588641870","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.701566Z"},"links":{"cited_paper":"/paper/2310.15318","citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:eb9487627d66cb24f6122fc2aa0b1026e50d0bc8a8b07157c9d7d71f8fc9116d","observation_id":"aa26be68-8002-458d-843c-ed5df4262205","resolution":{"observed_at":"2026-08-06T18:12:28.160167Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.02027","last_updated":"2025-05-04T08:30:00Z","snapshot_observed_at":"2026-08-07T15:56:40.275176Z","submitted_at":"2025-05-04T08:30:00Z","title":"GraphPrompter: Multi-stage Adaptive Prompt Optimization for Graph In-Context Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.02027","snapshot_observed_at":"2026-08-06T18:12:26.736464Z","title":"Graphprompter: Multi-stage adaptive prompt optimization for graph in-context learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.736464Z"},"links":{"cited_paper":"/paper/2505.02027","citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:9b9dc38efd2580838dc06bfe09b160cb40a71305159c6e35ef78ca05b6b11b73","observation_id":"71b92466-6752-42e8-b482-93f572e71fd1","resolution":{"observed_at":"2026-08-06T18:12:26.736464Z","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":"2026-08-06T18:12:29.422681Z","title":"Prompt tuning for graph neural networks,","venue":null,"work_id":"20496244-b538-468c-9b03-ea36780c680a","year":2022},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.766084Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:2432675603a82b01e74db4b3d3e4aa97346debe1bb2da6da3131f0e041196309","observation_id":"e0758393-ba5a-4e04-95a3-769a4da28a34","resolution":{"observed_at":"2026-08-06T18:12:29.433225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.387897Z","title":"Virtual node tuning for few-shot node classification,","venue":null,"work_id":"935057f1-f2ad-4f9c-a984-a7724ac528e2","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.799496Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:8c7f3288bda5caaf7c3f38da754478d5ad9bc992512885ba6d801049773013ba","observation_id":"2463f172-f39c-41da-af3c-8101cdc69e75","resolution":{"observed_at":"2026-08-06T18:12:29.402697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.359866Z","title":"Lvm-med: Learning large-scale self-supervised vision models for medical imaging via second- order graph matching,","venue":null,"work_id":"bd9f10dc-8720-4270-9d45-c80440d72a32","year":2024},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.834157Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:35e90193a0311551175771f6a5ccc0f67aa0d6a0e003a05603409c1a1105b474","observation_id":"e23c5a01-326d-454f-9390-d4b3fb21a945","resolution":{"observed_at":"2026-08-06T18:12:29.370981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03349","last_updated":"2023-08-07T07:03:49Z","snapshot_observed_at":"2026-08-07T09:30:32.107884Z","submitted_at":"2023-08-07T07:03:49Z","title":"SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03349","snapshot_observed_at":"2026-08-06T18:12:26.867540Z","title":"Scigraphqa: A large-scale synthetic multi- turn question-answering dataset for scientific graphs,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.867540Z"},"links":{"cited_paper":"/paper/2308.03349","citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:b3328f44c61dd7cbd4a03b29b7a55b7271d11fa725aae19375bc9f16cdc64484","observation_id":"8f0f219a-4a6f-4873-ac44-96b40b2cf966","resolution":{"observed_at":"2026-08-06T18:12:26.867540Z","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":"2026-08-06T18:12:29.328764Z","title":"Protein multimer structure prediction via PPI-guided prompt learning,","venue":null,"work_id":"eccb2a57-fb64-4eae-81e1-5036c55c70a6","year":2024},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.888689Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:c1c02472273d4280d38c56f6b65039d0fff2632def592b7c1ceceda57f357d3e","observation_id":"45159743-0cdf-4b8d-b705-f615ff4fe980","resolution":{"observed_at":"2026-08-06T18:12:29.338278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.291773Z","title":"XPrompt: Exploring the extreme of prompt tuning,","venue":null,"work_id":"0de34d1b-5c7d-4aab-8b96-37962a8f23f8","year":2022},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.920510Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:46c9ba1c76edce2fed8e682933e00ad863866d02dd6963289243a8a0afd22eaf","observation_id":"32625de9-69a2-43b4-8840-c8b832fb3140","resolution":{"observed_at":"2026-08-06T18:12:29.307659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.250731Z","title":"Towards locality- aware meta-learning of tail node embeddings on networks,","venue":null,"work_id":"6c296e3c-e743-4845-8f50-e35e0e589373","year":2020},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.952123Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:054e44823126e3ab5af0fca7baa32c80c4f5eb0d73587c07149bff2becb352e9","observation_id":"3091f080-2322-465e-80a7-baa23df120a7","resolution":{"observed_at":"2026-08-06T18:12:29.266884Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.207050Z","title":"Universal prompt tuning for graph neural networks,","venue":null,"work_id":"dc71624f-ea15-4a14-9d0f-a212242142b6","year":2024},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:26.989324Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:2a76d27145fbc0c56c99f999ce6380e7d4be338c2ea02e4821fa5e7455af5614","observation_id":"9855c759-468d-41f3-aa45-30d270ca7b47","resolution":{"observed_at":"2026-08-06T18:12:29.217475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.164701Z","title":"Are sixteen heads really better than one?","venue":null,"work_id":"05db2cf1-7c68-42a8-b7f7-d858cc94f1d2","year":2019},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.021903Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:6f6e3bd7e879eeecd435dd0b7453501d68f517cd6ed64abe0d69d8ee22f6d23f","observation_id":"8b8189dc-c7b0-4ed3-8036-4796e5cb9a2c","resolution":{"observed_at":"2026-08-06T18:12:29.187797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.133560Z","title":"Network together: Node classification via cross-network deep network embedding,","venue":null,"work_id":"7c79fdf6-045c-44df-b898-1a7eb9510863","year":1935},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.048762Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:173069bcf6994aa5222645e343a45e6c409b1a5f73b55503661faf12eef6394f","observation_id":"13e7a364-5d31-40e6-b5a7-e116b64dfb1f","resolution":{"observed_at":"2026-08-06T18:12:29.146956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.114324Z","title":"Neighborhood attention networks with adversarial learning for link prediction,","venue":null,"work_id":"36f042b0-ee2c-412c-b2d6-b713eac5d5dd","year":2020},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.085437Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:ead5cc1355cd1112e0e9c394140158321ba8dfd862e4e121d39e013d3d6086b6","observation_id":"7b00c638-5654-4b1d-a817-f4783a975068","resolution":{"observed_at":"2026-08-06T18:12:29.122394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:29.069325Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks,","venue":null,"work_id":"7aba8a51-078e-4e39-96c3-b2f68bac1fb8","year":2019},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.118672Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:17785434b583b7de66760f918aaef5e8db501b2a45957b083f1d751f5ea25140","observation_id":"f40287e8-70eb-429f-877b-f28e5e495e0b","resolution":{"observed_at":"2026-08-06T18:12:29.085587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-07-06T05:10:16.862707Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-06T18:12:27.154970Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.154970Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:f4e537f454c04016a3b889f0ad0f93b860f588041aac62e0ad41ca76c652ac35","observation_id":"0fe88ee4-398f-44aa-b8e8-0dfa98e3d711","resolution":{"observed_at":"2026-08-06T18:12:27.154970Z","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":"2026-08-06T18:12:29.022263Z","title":"Graph attention networks,","venue":null,"work_id":"f67be2cc-577b-436d-8bf0-c71f4bc23e60","year":2017},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.190002Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:870fbf9b4956376375ee8364e6c5e8c062e94c8c11ea70dcebaffe4a1ce6e82e","observation_id":"869c8f8d-b117-4be0-8aa0-10b903ca57af","resolution":{"observed_at":"2026-08-06T18:12:29.038687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.986684Z","title":"Graph contrastive learning with augmentations,","venue":null,"work_id":"8fec1461-85ce-422e-b020-f16432081bce","year":2020},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.212959Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:b4c21561cbdb0d7d94e778aab1dda999e7a6cd6bc16de239e3146d9c14642e47","observation_id":"a8febe66-4804-4985-bd81-9d92c2414ecf","resolution":{"observed_at":"2026-08-06T18:12:28.998100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.945198Z","title":"Commonsense knowledge base completion with relational graph attention network and pre-trained language model,","venue":null,"work_id":"f4eb568e-52af-46c9-8f33-3fef3cd0bb54","year":2022},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.237279Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:743dec56ae8ac38756f42eaa3b80c9c3b130198c823f29d23fed28339775abc3","observation_id":"fd27ffdd-6e0f-4b37-9c8c-566dcedbfae4","resolution":{"observed_at":"2026-08-06T18:12:28.959322Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.904142Z","title":"Graph neural network with curriculum learning for imbalanced node classification,","venue":null,"work_id":"76a9d38f-5b57-4ae0-8aba-e93c7c2c1cd8","year":2024},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.272426Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:3e5667827fcc8d6a9dff6327026411e615cc46bf1eed20e9ac4b2d45e1a09210","observation_id":"b24ea218-d2f7-4f9a-b4fb-fc109134a153","resolution":{"observed_at":"2026-08-06T18:12:28.925410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.874654Z","title":"Pooling architecture search for graph classification,","venue":null,"work_id":"3d5010d7-8e7f-4cce-89a8-f52e1f0e8663","year":2021},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.307410Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:e4efa16796e9fa46234b68a0f83132c518d3b197cd62793cb1bd8f65fca59e44","observation_id":"30306b3f-2ffd-4cf5-857d-a7a4b65cfc23","resolution":{"observed_at":"2026-08-06T18:12:28.888567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.834850Z","title":"Bring your own view: Graph neural networks for link prediction with personalized subgraph selection,","venue":null,"work_id":"b18a1459-42be-4f36-99db-0d86a1b6fd2a","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.344220Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:947190d78e3232f96919131d9f7ab4c061ec9299f5d85bdc66d7728078e5a092","observation_id":"c933ca46-ead0-4d39-a249-5dda7b67d31d","resolution":{"observed_at":"2026-08-06T18:12:28.859706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-06T18:12:27.378942Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.378942Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:dfd96475eb2cb5d17474b3e2cbf93c896ff984f7c9cd632732ed2912604d84eb","observation_id":"21303d98-5802-44fd-81f1-73bb8438e47a","resolution":{"observed_at":"2026-08-06T18:12:27.378942Z","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":"2026-08-06T18:12:28.803427Z","title":"Learning representations of inactive users: A cross domain approach with graph neural networks,","venue":null,"work_id":"dcf6ca92-1d00-444c-bd2e-a000e66a488e","year":2021},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.405472Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:7ccf1daad37b4ef7f34559f36be96e8dadf7222a43253245f73e19c336b8cec9","observation_id":"28e6e16f-6832-49aa-b06f-f8e2e1d0d18a","resolution":{"observed_at":"2026-08-06T18:12:28.814527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.764384Z","title":"Cross- domain few-shot classification based on lightweight res2net and flexible gnn,","venue":null,"work_id":"7afa1d84-101c-4d96-abe1-5c609ce7ff59","year":2022},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.441896Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:9254e5e3d3d08cc2fa82fe91faf977c08de1c93a89ba2086147c1b6327aed35d","observation_id":"f0a998d2-e0d0-4faf-be7a-e8468e3bd224","resolution":{"observed_at":"2026-08-06T18:12:28.783155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.732927Z","title":"Does gnn pretraining help molecular representation?","venue":null,"work_id":"7e96ade9-048a-4b1a-8de7-07c044953764","year":2022},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.475041Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:6a6030d6b9cd6b056234af5eec998909dccdc405ce80ebee6d0a79e7dd14aaf5","observation_id":"0fbb52ce-cbaf-4d46-a5fa-750126a203e2","resolution":{"observed_at":"2026-08-06T18:12:28.747187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.677689Z","title":"Robust self-supervised structural graph neural network for social network prediction,","venue":null,"work_id":"f79e3d2b-09c3-4e93-9ed4-d07a4735b306","year":2022},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.501938Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:2b33cec0eeae37bfe75bec3e25e561b9f7557f1f14851b08758edfb1ae4d2f7d","observation_id":"f19b2170-14ef-4950-b5bd-75fb257a448f","resolution":{"observed_at":"2026-08-06T18:12:28.706834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.637287Z","title":"All in one: Multi-task prompting for graph neural networks,","venue":null,"work_id":"5da1fc34-4ad8-456c-a3a7-4ec546607228","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.524625Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:92cfccb06fe72969cdbc6b168df329a5e001fa09019dafd6e5cf07d725b64316","observation_id":"e851c50d-85ff-4384-8946-c47218cedb8e","resolution":{"observed_at":"2026-08-06T18:12:28.649311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.601738Z","title":"Prodigy: Enabling in-context learning over graphs,","venue":null,"work_id":"5837a996-0164-44b9-8f21-6fd21c1d839c","year":2024},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.557366Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:b6f1875a676a8a60662014a3654b17f8f37752ec881e7eb998731f07ce9a321d","observation_id":"058cfdbf-5119-4bab-afa7-5a488ce5d90d","resolution":{"observed_at":"2026-08-06T18:12:28.621570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14845","last_updated":"2023-12-17T08:16:44Z","snapshot_observed_at":"2026-07-06T16:37:07.197221Z","submitted_at":"2023-10-23T12:11:13Z","title":"ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt","version":2},"cited_work":{"arxiv_id":"2310.14845","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.14845","snapshot_observed_at":"2026-08-06T18:12:28.026445Z","title":"ULTRA-DP: Unifying Graph Pre-training with Multi-task Graph Dual Prompt","venue":"cs.LG","work_id":"74cb1c1d-bb7f-477a-9bc8-e4ac029d0a95","year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.585534Z"},"links":{"cited_paper":"/paper/2310.14845","citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:f48ba4246288610985b8dcc561417ceb9c2a271d23ae967aefaa5b014a172cf0","observation_id":"11f3b67a-e6db-41fc-a68e-380e3b6c851c","resolution":{"observed_at":"2026-08-06T18:12:28.060637Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.564653Z","title":"Heterogeneous graph attention network,","venue":null,"work_id":"9f88ba52-d498-4d9f-a7f6-a37ba8d3babd","year":2019},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.621244Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:a75a1e8a13bcd19f15408fa45909a62d88af961b632371512a9bedbf34939c97","observation_id":"7ee866a3-64cf-4840-9adc-b6480bba0079","resolution":{"observed_at":"2026-08-06T18:12:28.576495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.515758Z","title":"Are we really making much progress? revisiting, benchmarking and refining heterogeneous graph neural networks,","venue":null,"work_id":"f85847b7-ecc0-4031-8b5c-83448c209530","year":2021},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.656685Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:026cc62ee4b49e56f4cfe9e17417e7d7c76b706416eada5c353fe574881fea61","observation_id":"744504d0-e524-434f-9a25-4ec585e7dfde","resolution":{"observed_at":"2026-08-06T18:12:28.539902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.466051Z","title":"Freebase: a collaboratively created graph database for structuring human knowledge,","venue":null,"work_id":"259962b1-3f5d-49f5-898a-0ddc5ecca58c","year":2008},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.691316Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:ec2d38516fe3d659969f057b4453a27ad77d707a758ad228fc4ef8466b763f49","observation_id":"f9e2ca2a-f856-443a-856b-179ed72bb2bb","resolution":{"observed_at":"2026-08-06T18:12:28.488809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.10341","last_updated":"2018-12-21T15:44:59Z","snapshot_observed_at":"2026-07-06T07:04:37.077852Z","submitted_at":"2018-09-27T04:53:24Z","title":"Deep Graph Infomax","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.10341","snapshot_observed_at":"2026-08-06T18:12:27.713644Z","title":"Deep graph infomax,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.713644Z"},"links":{"cited_paper":"/paper/1809.10341","citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:e6ebd781e2e17af50dc5f220eddb410c11c8ddbbff1eb1591aebb1556b027b98","observation_id":"c6f2a50e-5070-4c5d-be51-798b2497d993","resolution":{"observed_at":"2026-08-06T18:12:27.713644Z","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":"2026-08-06T18:12:28.405925Z","title":"Graph contrastive learning automated,","venue":null,"work_id":"b91f66e6-397f-4739-bed9-f46c70b33bec","year":2021},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.746716Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:7152f50f618fc40e977b2f475cb17f045dab54b8abb13749807a1cb44abe0d85","observation_id":"85413eaf-4551-4379-ab83-51fbc12623d2","resolution":{"observed_at":"2026-08-06T18:12:28.429874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.343393Z","title":"Contrastive pre-training of gnns on heterogeneous graphs,","venue":null,"work_id":"858a1681-99ea-4987-bf63-1d4a286b86fd","year":2021},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.794106Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:daa019bc8ea91651169477891d01248947aa19eac37cc806dba4fc40f23615ce","observation_id":"b5f2f73f-54aa-4718-9c04-10684f4db4f3","resolution":{"observed_at":"2026-08-06T18:12:28.372358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.292439Z","title":"Self-supervised heterogeneous graph neural network with co-contrastive learning,","venue":null,"work_id":"29e4eeff-6799-44d9-9d50-d2f31bd313a4","year":2021},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.828175Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:7152c4e68f3a02cbf83deb144bdf6c82bbcccc07271afac3ed5d45f2e0b02f06","observation_id":"d16aa4a9-c56a-431e-ab95-c70cdba96a5b","resolution":{"observed_at":"2026-08-06T18:12:28.312480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:12:28.251882Z","title":"Graph few- shot learning with attribute matching,","venue":null,"work_id":"3279d0ff-3b36-4251-9192-49d6b85c8b3f","year":2020},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.861895Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:ab967679042a25fbedebcb481c0cba484e09feb16ee13eef0b92562dfe50936e","observation_id":"4eb39084-ce2c-4eeb-871b-d4be0f1fcc27","resolution":{"observed_at":"2026-08-06T18:12:28.266674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16534","last_updated":"2023-11-28T05:36:59Z","snapshot_observed_at":"2026-07-06T16:53:35.776613Z","submitted_at":"2023-11-28T05:36:59Z","title":"Graph Prompt Learning: A Comprehensive Survey and Beyond","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.16534","snapshot_observed_at":"2026-08-06T18:12:27.890230Z","title":"Graph prompt learning: A comprehensive survey and beyond,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.890230Z"},"links":{"cited_paper":"/paper/2311.16534","citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:027ffaf71b2a6d1ba710ac5a86478c9b5b096fbdfed2604b0fff938b97c40353","observation_id":"487cfac6-7c28-424d-ab96-3750adfc5445","resolution":{"observed_at":"2026-08-06T18:12:27.890230Z","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":"2026-08-06T18:12:28.191066Z","title":"Relative and absolute location embedding for few-shot node classification on graph,","venue":null,"work_id":"8683703a-ac72-4575-8b1c-a49439df3505","year":2021},"citing_paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T18:12:27.928253Z"},"links":{"citing_paper":"/paper/2507.09132"},"observation_digest":"sha256:b0aaa1bca51bd3d593eb4610771f672db18dfc1d54de55fa87276aebbbe54121","observation_id":"23c99f5f-af1b-4016-a533-b439264d45c6","resolution":{"observed_at":"2026-08-06T18:12:28.218594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.09132","last_updated":"2025-07-12T04:12:24Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T18:00:56.772904Z","submitted_at":"2025-07-12T04:12:24Z","title":"Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":2,"verified_fuzzy":49},"total_outbound_references":58},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 2 inbound Pith citation observations for arXiv:2507.09132."}