{"as_of":"2026-08-10T07:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bbd42027b480d75af44748b726ad73488f0fca36f6730bef1d9ed6a28feca15c","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:49:14.516202Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.07405/citation-record","integrity":"/paper/2507.07405/integrity","json":"/paper/2507.07405/citation-record.json","paper":"/paper/2507.07405"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:49:23.746508Z","title":"Knowledge-preserving incremental social event detection via heterogeneous gnns","venue":null,"work_id":"d7f1e00b-8adc-41bc-8816-43ffad0596bb","year":2021},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:09.284843Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:9a6356e1181f16bab7a32f34d2171dce088146851b1114fdfaad4250994a2495","observation_id":"4391e80b-edaf-4891-b52a-000394ef7636","resolution":{"observed_at":"2026-08-06T18:49:23.871872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.12265","last_updated":"2020-02-18T19:49:48Z","snapshot_observed_at":"2026-08-04T16:33:25.229105Z","submitted_at":"2019-05-29T08:11:52Z","title":"Strategies for Pre-training Graph Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.12265","snapshot_observed_at":"2026-08-06T18:49:10.134810Z","title":"Strategies for pre-training graph neural net- works","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:10.134810Z"},"links":{"cited_paper":"/paper/1905.12265","citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:49ba47c29244be1708fbb4bcee5f4dc5363a51efbdc20744a5cfc81fa55d49d5","observation_id":"7b7717ab-9cf8-4813-ba60-e0e4aeecf33d","resolution":{"observed_at":"2026-08-06T18:49:10.134810Z","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":"2026-08-06T18:49:21.733027Z","title":"Heterogeneous graph transformer","venue":null,"work_id":"a3963a94-284d-4643-acc7-e563a48a2372","year":2020},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:10.318645Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:77d12c3dbd5d454f3bd846e7a6f37105705f3dc26f5bdb1fabeba2861a8c2ae3","observation_id":"3627b214-1ff9-47ff-abee-019f49bbcec8","resolution":{"observed_at":"2026-08-06T18:49:21.915939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:21.335079Z","title":"Prodigy: Enabling in-context learning over graphs","venue":null,"work_id":"bdd849c1-e2aa-4f06-b4fa-37c505dac5d1","year":2024},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:10.497776Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:e3cff1b888471a4f88bd098204d8989328776fe49635b3ec0a3e3e79d1c0de83","observation_id":"3984cdcb-2e14-4b86-a21d-6caf0e58ef7e","resolution":{"observed_at":"2026-08-06T18:49:21.537673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:21.040723Z","title":"A survey on knowl- edge graphs: Representation, acquisition, and applica- tions","venue":null,"work_id":"2a1f5293-9cff-4b98-9c07-e2c2c137547e","year":2021},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:10.702478Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:5890600e013a9078e2599058cf12f6807fc25ff959fd22f66d3568c41e55eef4","observation_id":"4083e4de-56d0-487d-bbe4-c621e4d33470","resolution":{"observed_at":"2026-08-06T18:49:21.164550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:20.639549Z","title":"Hdmi: High-order deep multiplex infomax","venue":null,"work_id":"9ab9c847-4091-442c-9130-b5836251495b","year":2021},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:10.858926Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:d58c5579efd306b593d5c4695b60494b5de40ec312376c2794388423264002d6","observation_id":"4b669f7b-7b64-4c10-ad68-d159c1a6b42b","resolution":{"observed_at":"2026-08-06T18:49:20.837445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:20.269130Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":"e0237fc3-64bc-4267-92b0-673eabc5e18c","year":2016},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:11.000300Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:6c44b5ce21460de11d98bce98f81a5eca8ec607240c112a94683125acd5ec36e","observation_id":"fa09ff4b-8393-4bc4-bea0-19c6e7bcdaf5","resolution":{"observed_at":"2026-08-06T18:49:20.469456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:19.595301Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"11439b6c-eaca-41a7-a50a-ecfdfb4289d4","year":2021},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:11.295894Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:bc97ec7ec0621e3cf82628af7978bec8a4c72aa71e9be618d659fa93f61462fc","observation_id":"0e480219-97bd-4366-99c5-1f5db22ecc6d","resolution":{"observed_at":"2026-08-06T18:49:19.761972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:19.328408Z","title":"Prefix- tuning: Optimizing continuous prompts for generation","venue":null,"work_id":"e67adb6e-cfee-408d-bad5-6f3d728d4674","year":2021},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:11.466838Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:e7826494713e1e90b35aedbe32238b236c9a49c99967f0b348f01bbd2c6a7444","observation_id":"ef3d9cb3-38da-4e89-9f15-940792fc7c62","resolution":{"observed_at":"2026-08-06T18:49:19.452579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:19.002471Z","title":"Graphprompt: Unifying pre-training and downstream tasks for graph neural networks","venue":null,"work_id":"d9019a1b-9c78-4f06-a0ce-cc4f0ffc911a","year":2023},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:11.663996Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:0a830d99af8a84cfeeb2422cb06e2441f56b49cd2c530ed6298516193f205af2","observation_id":"9ca3b506-4727-48db-b290-1e5967b8ec91","resolution":{"observed_at":"2026-08-06T18:49:19.142558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:18.660131Z","title":"Are we really mak- ing much progress? revisiting, benchmarking and refining heterogeneous graph neural networks","venue":null,"work_id":"d671d8ca-c2d9-4d98-99cf-322fdab7803d","year":2021},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:11.832168Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:4b749788ffd06f15e836883325c721da945e02d251f723ebe0ca2066f9201a3c","observation_id":"f1023d67-f915-4cc3-ac64-815f3e24d54e","resolution":{"observed_at":"2026-08-06T18:49:18.820289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:18.428500Z","title":"Hetgpt: Harnessing the power of prompt tuning in pre-trained heterogeneous graph neural networks","venue":null,"work_id":"838c13b1-b50e-40ab-8eba-877d6319ca84","year":2024},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:11.948253Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:0496a3f27cd300f3b53dd927b04866cc663ed9ac3615379eb589b8a078d3cc66","observation_id":"c4df9d0e-f2dc-484c-8756-74bfd9997b7f","resolution":{"observed_at":"2026-08-06T18:49:18.513503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:18.254199Z","title":"Hinormer: Representation learning on heterogeneous information networks with graph trans- former","venue":null,"work_id":"7c406caf-77a0-4006-b40b-abfe7a96de0e","year":2023},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:12.128509Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:9b8bea2b23067d02bb3c321b4acadb34282e584d903ece9eea58683e193de163","observation_id":"6075917e-9a39-49a8-9a4c-50be92943ca8","resolution":{"observed_at":"2026-08-06T18:49:18.316679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:17.982015Z","title":"Weisfeiler and leman go neural: Higher-order graph neural networks","venue":null,"work_id":"2ed5e24b-0c3f-4217-9087-e1cdd6dbf67d","year":2019},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:12.255011Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:60fe85b563ee24ec67428c235ec89bf93fed60041460c1ec5d2d9b85fe2e6718","observation_id":"bcc47400-ea81-4e95-b9d7-fd82247580f2","resolution":{"observed_at":"2026-08-06T18:49:18.103061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:17.756878Z","title":"Unsupervised attributed multiplex network embedding","venue":null,"work_id":"f2c6e0b6-afd4-4ba3-b457-55e0d39e581f","year":2020},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:12.398220Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:4440a737b8db72eef7cb0ab2db148dfebdfc2feccb4c422d2fabfd5939df9ee2","observation_id":"967de90b-4123-4a07-9419-081d48f8daef","resolution":{"observed_at":"2026-08-06T18:49:17.824507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:17.483827Z","title":"Gppt: Graph pre-training and prompt tuning to generalize graph neural networks","venue":null,"work_id":"fda04db3-481c-4644-af7d-215c0f7356c4","year":2022},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:12.547824Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:486cce118901c66fe42625d9b070b01227317c0aabde60e9aeabf3864b75f90c","observation_id":"cc58424d-169b-46ef-bd89-1b03837d7648","resolution":{"observed_at":"2026-08-06T18:49:17.608743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:12.732082Z","title":"Graph prompt learn- ing: A comprehensive survey and beyond","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:12.732082Z"},"links":{"cited_paper":"/paper/2311.16534","citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:86b65cbabd87407944ee33ec5b4ef8a04394808e71e09e255c106e3412af382f","observation_id":"85e6406d-3474-45da-89ca-9e3fffd10a0f","resolution":{"observed_at":"2026-08-06T18:49:12.732082Z","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":"2026-08-06T18:49:17.177474Z","title":"Virtual node tuning for few-shot node clas- sification","venue":null,"work_id":"af2cccf3-628d-41d7-942c-c76bf0f4c3f2","year":2023},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:12.924230Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:c6d01cbd959fded372b67352db44d7a33208d7fb31ba3049462c01ef569a31bd","observation_id":"49a6cd69-b282-4c49-8734-59aaca0fcbef","resolution":{"observed_at":"2026-08-06T18:49:17.322860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-06T18:49:13.067777Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:13.067777Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:440e82c5a4d2fb5092d87cff2ece061317e119e9c8321d1d7c48d26c7cab5572","observation_id":"e92d563f-2c40-4e94-a7e4-6421be8d779b","resolution":{"observed_at":"2026-08-06T18:49:13.067777Z","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":"2026-08-06T18:49:16.600156Z","title":"Self-supervised heterogeneous graph neural network with co-contrastive learning","venue":null,"work_id":"b7ee3206-cb7b-4eeb-a560-e9bca5f15e8a","year":2021},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:13.329107Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:cfd678e8616e08c3bcf4d3362073fdca67d2d31ff8a440f10ddafe39b114a4c9","observation_id":"9634cbae-280a-4bf9-815f-9577c7539343","resolution":{"observed_at":"2026-08-06T18:49:16.725627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:16.289869Z","title":"Simgrace: A simple framework for graph contrastive learning without data augmentation","venue":null,"work_id":"b115c705-aa02-4119-bb3b-815dd2324df7","year":2022},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:13.458173Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:2db249d1855ea547177c62ed91fe2a2365f67e8e542e0eb6799ef75e0f73871c","observation_id":"e5b66de5-6b15-40b8-ab5c-cd9f04f3ca89","resolution":{"observed_at":"2026-08-06T18:49:16.449880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:15.812061Z","title":"From local structures to size generalization in graph neural networks","venue":null,"work_id":"c324011f-0097-407d-9650-2bf09b1d0c3b","year":2021},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:13.742229Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:f56a93e2b58f35ac1b48a2b0dd4e4e9fa82ddb500cfb322f89992c37e8744365","observation_id":"0d770f4c-aab5-4f75-adda-192db516db15","resolution":{"observed_at":"2026-08-06T18:49:15.885831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:15.606856Z","title":"Graph con- trastive learning with augmentations","venue":null,"work_id":"3ee007e3-169d-4668-88b3-7ece088fa8f9","year":2020},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:13.885275Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:bf79c9710ae85d110ee554bd7ab07de76ee3ff15b60f9d7a17a2479a3a8a3ddc","observation_id":"cc41381c-971a-423c-9e13-9b268e8263e7","resolution":{"observed_at":"2026-08-06T18:49:15.716095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:15.327939Z","title":"Hgprompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning","venue":null,"work_id":"504c5c39-ec48-43bf-bdbf-2d8a6e067cad","year":2024},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:14.073045Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:fda7d455a968f126d19de2bbf8dafb6e5fee31412c2b5f55ec468ef87646ce89","observation_id":"59eb6278-997f-4bab-aa00-d2b976829120","resolution":{"observed_at":"2026-08-06T18:49:15.431578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:15.066788Z","title":"Graph trans- former networks","venue":null,"work_id":"2208a83b-1243-458d-9291-7c797274059d","year":2019},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:14.290279Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:c632eb1d5d494e84d1d55de8f6cd795e0969477609d36bd8973ca30b5e035dd2","observation_id":"ff7fa0d2-0fa9-4770-ba6f-5e5d3351ae38","resolution":{"observed_at":"2026-08-06T18:49:15.205129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:14.776928Z","title":"Few-shot learning on graphs","venue":null,"work_id":"d55bd9d4-2bea-4af3-9778-9b04a097874b","year":2022},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:14.375884Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:b3f98f814ccf6d4d909aec49fbd159c85b644f4f5419e3ac434ea30eecf2175a","observation_id":"d9bfde4d-132f-4033-a690-2bbf070ed924","resolution":{"observed_at":"2026-08-06T18:49:14.954772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05346","last_updated":"2024-06-19T10:55:22Z","snapshot_observed_at":"2026-07-06T18:27:28.886692Z","submitted_at":"2024-06-08T04:17:48Z","title":"ProG: A Graph Prompt Learning Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.05346","snapshot_observed_at":"2026-08-06T18:49:14.516202Z","title":"Prog: A graph prompt learning benchmark","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:14.516202Z"},"links":{"cited_paper":"/paper/2406.05346","citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:65670e8f7032067cad59a9192bb265dd2d1957e9c0db0984730e4de17fdebce5","observation_id":"77c3171c-0226-46a4-a752-69288df6ab06","resolution":{"observed_at":"2026-08-06T18:49:14.516202Z","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":"2026-08-06T18:49:19.970984Z","title":"Understanding attention and gen- eralization in graph neural networks","venue":null,"work_id":"92c2b498-90c9-446d-952b-7926c187e0e2","year":2019},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:11.145470Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:5235ae156c24eb2e02a4e3764ad1087b6f99365b84f1f179b9fc2933eb72a08c","observation_id":"ecc44c19-608e-4ad8-b494-b35c096a029f","resolution":{"observed_at":"2026-08-06T18:49:20.128670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:16.868547Z","title":"Hetero- geneous graph attention network","venue":null,"work_id":"a80cfacb-1c19-41f0-aac3-81ab4f7fd838","year":2019},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:13.164561Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:bd2fe4c84a2a521a94d3fb5e10b7490cc26e7ea753d640872f96a79adb0874af","observation_id":"c6324ee3-a948-4490-8622-dc74db65eb6e","resolution":{"observed_at":"2026-08-06T18:49:16.993506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:23.231387Z","title":"Universal prompt tuning for graph neural networks","venue":null,"work_id":"70140e15-f349-4c21-b68e-1a122e1bd672","year":2024},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:09.557472Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:abf1d7e2132cde6183d00d337812317d6d23edc313d23b29303253e0645e50ce","observation_id":"c3b4d28c-3319-4460-949d-a30761bc554d","resolution":{"observed_at":"2026-08-06T18:49:23.359176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:22.483153Z","title":"A survey of graph neural networks for recommender systems: Challenges, methods, and directions","venue":null,"work_id":"36925bf7-5237-45d1-b1a8-43d645a229eb","year":2023},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:09.848066Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:c1393f5c348574203a71a0aa9684ba56fc59c3010eb0da5662eeed3a1e5e6aa6","observation_id":"857ca0a7-4e1a-4888-9731-a2d3c9c8deef","resolution":{"observed_at":"2026-08-06T18:49:22.653184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:23.497304Z","title":"Unified language model pre- training for natural language understanding and genera- tion","venue":null,"work_id":"fde98447-a760-4a4d-915c-f835a1cd212c","year":2019},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:09.416643Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:3ce8daad7b900ddc8a6aac2884f6e7cef3fcc292201c79b16dd9f57567237e04","observation_id":"79112a52-0f3a-4ae8-ac3e-1b477e0eb5a3","resolution":{"observed_at":"2026-08-06T18:49:23.585917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:16.001584Z","title":"Heterogeneous network rep- resentation learning: A unified framework with survey and benchmark","venue":null,"work_id":"7efbb1ef-128e-4c5b-895e-471a09ab78df","year":2020},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:13.644536Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:60bb3828c91257daa5fd3e37868dfd3f380c2a64e412a2af5fccef537a41bc00","observation_id":"52b47c15-8406-490d-91ee-32ce4a871a30","resolution":{"observed_at":"2026-08-06T18:49:16.119108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:22.115543Z","title":"Knowledge graphs","venue":null,"work_id":"8c7d13bc-f986-4c49-b66d-16665160989d","year":2021},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:09.977658Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:e34175920ff606670a75129ada63da795c01dd29c6f07b4d48d33586c498927b","observation_id":"6a17344d-a5d7-410b-b31a-4c00c2bd993d","resolution":{"observed_at":"2026-08-06T18:49:22.313735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:49:22.871935Z","title":"Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding","venue":null,"work_id":"4d8c6b2b-c54c-4bb3-865d-d4eb54b941c4","year":2020},"citing_paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T18:49:09.698229Z"},"links":{"citing_paper":"/paper/2507.07405"},"observation_digest":"sha256:d7c4cf6eaa8ba4566c216693720107a3dec8154e0bfb2447a007dd1957760667","observation_id":"584056e4-0a1d-449a-955e-194cb13b51c8","resolution":{"observed_at":"2026-08-06T18:49:23.058110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.07405","last_updated":"2025-07-10T04:01:47Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T18:39:34.554864Z","submitted_at":"2025-07-10T04:01:47Z","title":"HGMP:Heterogeneous Graph Multi-Task Prompt Learning"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":31},"total_outbound_references":35},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2507.07405."}