{"as_of":"2026-08-09T16:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dac714b753fe3427925ab542314408f5d084b68453b19f9fe4166a380ad6360c","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T00:14:05.772560Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2608.04255/citation-record","integrity":"/paper/2608.04255/integrity","json":"/paper/2608.04255/citation-record.json","paper":"/paper/2608.04255"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.646324Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.646324Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:be952e6a47860d1c41be716e4297ea4f05858268206a63e525fe59d225ec68f7","observation_id":"b9bb3031-fb2b-46f3-88a9-2afb72ffbc9b","resolution":{"observed_at":"2026-08-08T00:14:05.646324Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.650440Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.650440Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:da4131b138b03c911a7c5509d2a5d3a4e13ddef597248c388bede3af4529a587","observation_id":"8b4b8a13-4ab6-403e-b267-36a2a7890bcf","resolution":{"observed_at":"2026-08-08T00:14:05.650440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08170","last_updated":"2024-04-11T05:01:12Z","snapshot_observed_at":"2026-08-04T08:10:16.676870Z","submitted_at":"2024-02-13T02:03:26Z","title":"LLaGA: Large Language and Graph Assistant","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.08170","snapshot_observed_at":"2026-08-08T00:14:05.654019Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.654019Z"},"links":{"cited_paper":"/paper/2402.08170","citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:d5fd3721d06f995918327beb9d71c6e09b2b135dc426931db92535063b1c9f7d","observation_id":"48925885-2055-4150-9c06-37dbc5cec20f","resolution":{"observed_at":"2026-08-08T00:14:05.654019Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.658007Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.658007Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:c13931142349f538c0b96748cce87cc7a6c10c7db068595517573ae14c89d293","observation_id":"e8723c18-ed4c-4b63-920c-d81a375b1975","resolution":{"observed_at":"2026-08-08T00:14:05.658007Z","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":"2026-08-08T00:14:06.120501Z","title":null,"venue":null,"work_id":"8f396102-3146-457f-b88d-4237a0ba2415","year":null},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.662162Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:73b455f214001a769a003db79dcac8c80f3a753af46ffc51ab9f9df6cad59a13","observation_id":"fd9580ca-2ce4-486b-b2fb-f1c41862371c","resolution":{"observed_at":"2026-08-08T00:14:06.123762Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.669165Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.669165Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:36c832f7f54751e3ed73ba6ecd13316a0c8e654ac18c442743ae85108ed48dea","observation_id":"5786884b-4a54-4a74-a9b9-3dc290c86b5b","resolution":{"observed_at":"2026-08-08T00:14:05.669165Z","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":"2026-08-08T00:14:06.095436Z","title":null,"venue":null,"work_id":"b2eb417b-27c8-4d55-a769-b8a28ef47b22","year":2024},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.672163Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:feba648b5ecdea841fd49fadc9d578a6dab2f8221faa5bcac95396fe4281ed82","observation_id":"2b83cbb2-35a0-41ad-a199-d8a4c9bb6442","resolution":{"observed_at":"2026-08-08T00:14:06.099122Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:06.086139Z","title":null,"venue":null,"work_id":"2729c157-07a7-41f0-b31a-c381672ae53c","year":null},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.674864Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:7b96112820fb4d4d8699654d605dab8bc178de04fecf37145dd8a5f8af502437","observation_id":"407bf0d3-c885-454d-9787-83f2f32ff8e2","resolution":{"observed_at":"2026-08-08T00:14:06.089337Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.680320Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.680320Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:dd61a37a73e0435319ff95bc43a6509f541bc6b7aaddcfc86d6995c5f000a7dc","observation_id":"01d0df58-5696-47ab-84eb-9406a8440590","resolution":{"observed_at":"2026-08-08T00:14:05.680320Z","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":"2026-08-08T00:14:06.075321Z","title":null,"venue":null,"work_id":"dfa77142-6f4a-490e-bf44-1fc95674b725","year":2023},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.677694Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:77ef1eea49d943296302d7dbc126eeeb4067bab88fbdada2aeccfbb1383bd9d6","observation_id":"a94a3ed6-ab9e-4b1c-9cd3-6ddb2a1487af","resolution":{"observed_at":"2026-08-08T00:14:06.079877Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.685907Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.685907Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:2c841d9a156f7b1216f5df8a4730be9d8620fc0aa2a69fa45eecb602c0deaeb0","observation_id":"d91b0e59-608f-44a0-aee6-1c7fc7f59ad7","resolution":{"observed_at":"2026-08-08T00:14:05.685907Z","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":"2026-08-08T00:14:06.059768Z","title":null,"venue":null,"work_id":"2332a464-8f0f-44d6-913a-0bfd2fd687fc","year":2026},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.683196Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:f3771f55ad24f6db58589f2567ba21ed2b95b353762c7ad937fd5ceae7585077","observation_id":"074b41b1-ff0d-4317-be2e-9dea996d8f2c","resolution":{"observed_at":"2026-08-08T00:14:06.063075Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:06.033899Z","title":null,"venue":null,"work_id":"9fd4b6a2-8c05-4c6b-97b5-accd8794b2b7","year":2025},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.693946Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:4c7338d1a31f7b66e74cf1961cf9040e6ae4494ff2e8f5a86b3b5b0b35d22911","observation_id":"86919525-3d29-4e49-a854-ba075c32cd72","resolution":{"observed_at":"2026-08-08T00:14:06.037392Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.09205","last_updated":"2022-03-17T09:56:32Z","snapshot_observed_at":"2026-08-04T11:39:38.366462Z","submitted_at":"2022-03-17T09:56:32Z","title":"SoK: Differential Privacy on Graph-Structured Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.09205","snapshot_observed_at":"2026-08-08T00:14:05.697117Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.697117Z"},"links":{"cited_paper":"/paper/2203.09205","citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:ce9a1548d9e2a1994eb80ebaa3c353063b8a07544a2396eec86997865ee85be0","observation_id":"382f7206-1f4f-4eca-b299-b734baf3cd38","resolution":{"observed_at":"2026-08-08T00:14:05.697117Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.691305Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.691305Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:7959476be189a4531add3d3d5b0b0bc1c9431290010e9dbbea4a692d6b44e948","observation_id":"8d86cec1-4cba-4d15-a54b-021cd7f8e249","resolution":{"observed_at":"2026-08-08T00:14:05.691305Z","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":"2026-08-08T00:14:06.015752Z","title":null,"venue":null,"work_id":"005973f8-c314-4328-ad35-0a08fc1a85a7","year":2024},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.704610Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:b0d8155b844c12855ccc5836f05a133a1ae27d3dd2653b99df0f6d6b14b7f483","observation_id":"46c507c1-d304-4be1-a65f-da728a4f8b28","resolution":{"observed_at":"2026-08-08T00:14:06.018624Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:06.006847Z","title":null,"venue":null,"work_id":"b660b2e4-f041-4487-bd9c-e6e38745443d","year":2024},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.707860Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:07049e4f647f2e74f6e26367e64edc9031b17173c7f75f3efec82ffc9fd66829","observation_id":"e8b0b33a-58f9-46ab-a048-972e9f7449cd","resolution":{"observed_at":"2026-08-08T00:14:06.009671Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:06.024500Z","title":null,"venue":null,"work_id":"7ea52592-9388-4053-a0e6-8e01eb623dd0","year":2023},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.701516Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:886d539f88c509339e196a4599bba99e7c0344ea8fbc9991d2b7ff5043b6a157","observation_id":"dae425b7-1acd-487d-9c0f-1709bb1fd739","resolution":{"observed_at":"2026-08-08T00:14:06.027768Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.989896Z","title":null,"venue":null,"work_id":"fcb6f233-5aec-451c-aed6-bf436a548ea4","year":2025},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.714181Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:6eedad81d9297756cb18619cf3d188669090a97d27f82273c6a1ef307e6d509c","observation_id":"a9252f93-c3c8-426e-a29a-938fb98ab889","resolution":{"observed_at":"2026-08-08T00:14:05.992634Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.979169Z","title":null,"venue":null,"work_id":"1c483157-8faf-46de-8466-218741426feb","year":2021},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.717404Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:be0519299c0575276e8c7e17c44180644e5f97eadcef8ea845d0a98a9fccda29","observation_id":"6acc2e07-75fa-4454-a56e-84136fc87cec","resolution":{"observed_at":"2026-08-08T00:14:05.982876Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.998304Z","title":null,"venue":null,"work_id":"87ad270a-9e6f-42e2-a14a-02b7f0fa5880","year":2016},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.711169Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:7747d3850558f73421552fafced6ecd3e4838d47c95da564cfe85ed2c002760f","observation_id":"dfa63c7e-b810-42ae-95bb-665c20bbc717","resolution":{"observed_at":"2026-08-08T00:14:06.001106Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.957574Z","title":"2023.{GAP}: Differentially private graph neural networks with aggre- gation perturbation","venue":null,"work_id":"0af01309-3e1c-45aa-aa71-0a283fb2626e","year":2023},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.723780Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:13eecbc3ba2f41d3ce4c3b10e79c0858b0b9a4fbbe0c05b6e8297aa34f6fd68a","observation_id":"7fa74507-eba6-4201-b736-f55a6c6ab0c0","resolution":{"observed_at":"2026-08-08T00:14:05.962076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.948421Z","title":null,"venue":null,"work_id":"01073e81-ef16-4580-8336-1917a26a49f6","year":2016},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.726833Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:31944962dccecd589cfec9900c6055495470dedfb5b3a6fb614d18d31a789b6a","observation_id":"84a90f1e-f2a9-465a-ad5e-5cfc70e85320","resolution":{"observed_at":"2026-08-08T00:14:05.951617Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.968317Z","title":null,"venue":null,"work_id":"e67d3159-6ec3-4b94-bb55-fdec1e9fa109","year":2024},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.720703Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:bd0afd6ce6fea29f71a13a74a2be8061a952d9afa1cd5e0b07541d323113ea4b","observation_id":"a0550d19-07d8-435b-986e-3619aec37101","resolution":{"observed_at":"2026-08-08T00:14:05.972357Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.939263Z","title":null,"venue":null,"work_id":"3e005297-7cc9-4778-a587-556972dd3705","year":2022},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.733554Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:a300417066155a35f231542255b8336e289cd034d622d63fd9fb4f973fd2a60e","observation_id":"8c07dacf-f33c-4e40-b8dd-621c4eb663f0","resolution":{"observed_at":"2026-08-08T00:14:05.942327Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.929786Z","title":null,"venue":null,"work_id":"01cf3fde-8011-4c24-8225-c7d33e9091e7","year":2025},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.736698Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:e087628a789f659e4a70889152dc4699091317a5e84ef78a504acef95fad3438","observation_id":"e43200f3-e836-444d-89b5-df87a48f6cac","resolution":{"observed_at":"2026-08-08T00:14:05.932888Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.09078","last_updated":"2021-09-19T08:06:04Z","snapshot_observed_at":"2026-07-06T11:49:14.106329Z","submitted_at":"2021-09-19T08:06:04Z","title":"Making the Most of Parallel Composition in Differential Privacy","version":1},"cited_work":{"arxiv_id":"2109.09078","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.09078","snapshot_observed_at":"2026-08-08T00:14:05.832665Z","title":"Making the Most of Parallel Composition in Differential Privacy","venue":"cs.CR","work_id":"1995517b-17b3-44bd-9e7b-813634b26d02","year":2021},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.729908Z"},"links":{"cited_paper":"/paper/2109.09078","citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:5536cad27b4a9230a23cc3d4d9a692111e80c304c645911f9fcdf85429d27d44","observation_id":"144939ae-8872-4395-989a-520a70981a9e","resolution":{"observed_at":"2026-08-08T00:14:05.835883Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.915220Z","title":null,"venue":null,"work_id":"c5d4c697-a5f4-4d4d-815f-95d4c7342f0c","year":2004},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.743160Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:aca2d53651b012d814a16ead281519a46f5bf561cd8065e36264aa1e0f9af552","observation_id":"b2891c28-8e32-4471-b092-e18c5da457ef","resolution":{"observed_at":"2026-08-08T00:14:05.918396Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.746164Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.746164Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:61935e1014cd0460a2ba76b25915f08bedb494db20151939900dd083dae08a2d","observation_id":"152988f9-ba89-4b13-b489-b083d2eeb3e7","resolution":{"observed_at":"2026-08-08T00:14:05.746164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.739979Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.739979Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:98459c014668e6f2b4670a303fd98f6849c07bf3b356ad149bf3d3fc33770a5a","observation_id":"04df3df8-715b-4fac-aca6-cada831237f7","resolution":{"observed_at":"2026-08-08T00:14:05.739979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.20552","last_updated":"2023-10-31T15:34:59Z","snapshot_observed_at":"2026-07-06T16:41:11.586802Z","submitted_at":"2023-10-31T15:34:59Z","title":"Privacy-preserving design of graph neural networks with applications to vertical federated learning","version":1},"cited_work":{"arxiv_id":"2310.20552","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.20552","snapshot_observed_at":"2026-08-08T00:14:05.817452Z","title":"Privacy-preserving design of graph neural networks with applications to vertical federated learning","venue":"cs.LG","work_id":"1b9f9127-6d6e-4f6f-97af-6f63ad1132e0","year":2023},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.752274Z"},"links":{"cited_paper":"/paper/2310.20552","citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:255ab3d0557bbe5a01eaf6a4928f45841d420d8226794ed4a3b2b904893ee6af","observation_id":"5f1735d5-b609-456d-a105-bb491a22ddf0","resolution":{"observed_at":"2026-08-08T00:14:05.823320Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.07597","last_updated":"2024-09-24T03:01:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-14T10:57:50Z","title":"C-Pack: Packed Resources For General Chinese Embeddings","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.07597","snapshot_observed_at":"2026-08-08T00:14:05.755598Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.755598Z"},"links":{"cited_paper":"/paper/2309.07597","citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:8ea57ce743ef6cf7f90894d430b25427cd633c0d21f33c4f853920fe35d81cae","observation_id":"707805cd-766f-449a-9b10-07995257735b","resolution":{"observed_at":"2026-08-08T00:14:05.755598Z","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":"2026-08-08T00:14:05.899312Z","title":null,"venue":null,"work_id":"a77ccb23-78c4-4b74-bb56-91a146217a6c","year":2016},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.749118Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:08206d4c7d4697479b1e9d9d98fe8d890d3b9df540362d65696ab83764de825c","observation_id":"0516d98e-24d0-45d2-83ed-b3b5ee395f49","resolution":{"observed_at":"2026-08-08T00:14:05.902739Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00826","last_updated":"2019-02-22T19:15:54Z","snapshot_observed_at":"2026-07-06T07:05:24.565760Z","submitted_at":"2018-10-01T17:11:31Z","title":"How Powerful are Graph Neural Networks?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.00826","snapshot_observed_at":"2026-08-08T00:14:05.762280Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.762280Z"},"links":{"cited_paper":"/paper/1810.00826","citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:9d4818d2c68bfe77b7b05429b35f4592132863d2b5301966391d71857da4b00f","observation_id":"67ca14f3-552e-45af-89f5-d66ecde52f53","resolution":{"observed_at":"2026-08-08T00:14:05.762280Z","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":"2026-08-08T00:14:05.879563Z","title":null,"venue":null,"work_id":"be42e411-1109-4073-a96d-0e6110dd2810","year":2025},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.766131Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:2be83462f82691561de2e7a489e3d805052750a001bcd777c708b7d0c69edc80","observation_id":"e73afdc3-83f5-400e-a2da-7b458a50c98d","resolution":{"observed_at":"2026-08-08T00:14:05.883015Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.889177Z","title":null,"venue":null,"work_id":"b51d0495-0449-4439-a065-0a4dacedb897","year":2025},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.759237Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:6ede303ca191c4d6b3cfa81f4ed562ffe84027ce1078397b92c0da0c8f1acab1","observation_id":"92cefd2b-0df1-44c4-b98f-7f2e64ee554c","resolution":{"observed_at":"2026-08-08T00:14:05.893157Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.859576Z","title":"Yes”/“No","venue":null,"work_id":"64522787-84b0-4d4c-a41c-ba397b885b5e","year":2024},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.772560Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:3859af646cd57f394f4a0e145ab82c97e545cc6c8e3d794a01ab9da7a15b335e","observation_id":"37b6c146-7b27-43a2-ab31-e453df656fbd","resolution":{"observed_at":"2026-08-08T00:14:05.863159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.869842Z","title":null,"venue":null,"work_id":"55dcb7b7-dfa9-4bac-9c4f-4448321c04f5","year":2023},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.769185Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:46e7ce4dbf2e25a2e28313c69375e22064c718a94fab1780b0e0eadecf283f43","observation_id":"6580d392-5d51-4798-b3df-79b2d11131a1","resolution":{"observed_at":"2026-08-08T00:14:05.873189Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:14:05.688675Z","title":"Information Retrieval3, 2 (2000), 127–163","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":2000,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.688675Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:8df1ae7ab369c92fe0ca8cda6a3bc77d5417600f3ddec6368ae27e9037b9e7a8","observation_id":"780a834e-5cf2-4ce6-afe2-17394d10d1a2","resolution":{"observed_at":"2026-08-08T00:14:05.688675Z","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":"2026-08-08T00:14:06.110799Z","title":null,"venue":null,"work_id":"06048201-4400-4449-978c-9fa28b313d62","year":2023},"citing_paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-08T00:14:05.665703Z"},"links":{"citing_paper":"/paper/2608.04255"},"observation_digest":"sha256:4e487da3bd01892dabda7c79b73abb30921563b162b17309623719b0d775ffe8","observation_id":"b1150c44-4f33-4a2b-a9f9-5389b08a3bed","resolution":{"observed_at":"2026-08-08T00:14:06.114099Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.04255","last_updated":"2026-08-04T22:23:19Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-08T23:11:20.135491Z","submitted_at":"2026-08-04T22:23:19Z","title":"PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":36,"verified_exact":2,"verified_fuzzy":2},"total_outbound_references":40},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2608.04255."}