{"as_of":"2026-08-15T07:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bba7db43df01516cd72059ae811484752e2ea8fb0aa4e45fab51095c012363a3","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T11:25:20.078135Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2412.16250/citation-record","integrity":"/paper/2412.16250/integrity","json":"/paper/2412.16250/citation-record.json","paper":"/paper/2412.16250"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.954257Z","title":"Stochastic weight completion for road networks using graph convolutional networks,","venue":null,"work_id":"1e8d9836-c1b4-415e-98f7-2705e5b3da93","year":2019},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.811713Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:7c90384e50938a1693a629984888adde9f47c709834e8f17d66f3054f885e1bf","observation_id":"6563958a-e2bd-4b50-90ff-4918c227754a","resolution":{"observed_at":"2026-08-11T11:25:20.958943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.941258Z","title":"Predicting path failure in time-evolving graphs,","venue":null,"work_id":"6e8c5515-6c9e-44d2-9687-7967c567a813","year":2019},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.816470Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:cadea56da43381d99443a8918ef490424af6016c646875c27fff834c1c9410c1","observation_id":"a72d1e05-4941-40b0-8c42-680fe1255ca5","resolution":{"observed_at":"2026-08-11T11:25:20.945436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.927482Z","title":"Medical entity disambiguation using graph neural networks,","venue":null,"work_id":"b136b808-6cbe-4621-8c75-cdbd9ad62da9","year":2021},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.820921Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:2791d0cb4464fc0a7af79ca4a319c75a5e63fd06cbdede0033fbb16c6fc773ba","observation_id":"77009097-a74a-470a-845b-5e5cd6efe46f","resolution":{"observed_at":"2026-08-11T11:25:20.931609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.914637Z","title":"Graph transformation policy network for chemical reaction prediction,","venue":null,"work_id":"ec2723d2-25f6-48ab-abc4-de4944ff51d0","year":2019},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.825100Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:9f7ff31dfebaa82462d843893a25ff3f468d59e71f581bb97ff38b0ec9352652","observation_id":"f6523d42-2d49-4a91-9f16-c5fb67b46f4b","resolution":{"observed_at":"2026-08-11T11:25:20.918479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.900742Z","title":"Creating embed- dings of heterogeneous relational datasets for data integration tasks,","venue":null,"work_id":"69d31fd6-9626-42bf-8cdc-a9a9b003b924","year":2020},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.829433Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:9d3d0e7cdfcdbec7f5305222e82dc58dee9e5f956956d3eafd50ffb9d54ff521","observation_id":"c3aa63ff-cb22-47f8-82d2-0a60698b1c2b","resolution":{"observed_at":"2026-08-11T11:25:20.905382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.886785Z","title":"Estimating node importance values in heterogeneous information net- works,","venue":null,"work_id":"44274b3a-6e7b-45b2-9d7d-a193d5ad9f8e","year":2022},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.833944Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:5d572cc401b51205a856135ff1f8208cd59dc4f79a5f5114857d4fee0dbb20ec","observation_id":"84e282d4-396c-41c8-8a03-02bf427198d6","resolution":{"observed_at":"2026-08-11T11:25:20.891428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.871879Z","title":"Discovering maximal motif cliques in large heterogeneous information networks,","venue":null,"work_id":"3c85b483-1eb2-40eb-8460-147695cd2392","year":2019},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.839709Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:a342aae5b06e354710433c646839a5a581e86f22fba9ab4c500e2b63077ba8d0","observation_id":"ddb86eb1-a66f-48df-858f-3d07d905217e","resolution":{"observed_at":"2026-08-11T11:25:20.877750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.857553Z","title":"Are we really making much progress?: Revisiting, benchmarking and refining heterogeneous graph neural networks,","venue":null,"work_id":"71239a8d-0901-4e80-a9e6-478762333078","year":2021},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.844632Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:ad2ffe783de45584dd81da222101e3bc75c596df26a6b5268ce174c6fa630c30","observation_id":"aabaa197-41a6-47fa-9182-2c826247b5c4","resolution":{"observed_at":"2026-08-11T11:25:20.862391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.843659Z","title":"Heterogeneous graph attention network,","venue":null,"work_id":"8c0fd804-d236-43d4-b473-d77297939add","year":2019},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.848795Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:0b1ea5be902c94250eab214ed193f0ce80637d1f6bb22d8e57c07b57245f6876","observation_id":"63806f9b-e983-4054-8a2d-5669fcba2915","resolution":{"observed_at":"2026-08-11T11:25:20.848225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.830590Z","title":"Poskhg: A position-aware knowledge hypergraph model for link prediction,","venue":null,"work_id":"e6e360d4-5751-4346-84ec-8d737dbd7a97","year":2023},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.853114Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:9f2db524feb1d6e45051258dd2d1e553fdf309c891cb02ddf14ca11f4b4bf615","observation_id":"eb1d5ce9-592a-4a8b-8d3b-0855b8638e63","resolution":{"observed_at":"2026-08-11T11:25:20.834725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.817808Z","title":"Few-shot relation prediction of knowledge graph via convolutional neural network with self-attention,","venue":null,"work_id":"dac5f4e8-e676-4b7f-b699-f546ac87d5e5","year":2023},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.857398Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:8f1274acffa718682f7debb3f46b5d91218cbcbccc0a0d0cecfc327278c94d65","observation_id":"b12da066-3027-42a9-9122-94e97829233d","resolution":{"observed_at":"2026-08-11T11:25:20.822009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.804307Z","title":"Multiple types of disease-associated rnas identification for disease prognosis and therapy using heterogeneous graph learning,","venue":null,"work_id":"624610e5-23b8-48c5-9d69-2838cf06e052","year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.861961Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:f50589ced9ea972f73b0e5a884024da399526886b8e23258e25939cdc58b5727","observation_id":"5899f97e-f80c-4a5d-ac0b-da334eb8ea4c","resolution":{"observed_at":"2026-08-11T11:25:20.808540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.791661Z","title":"Label-aware chinese event detection with heterogeneous graph attention network,","venue":null,"work_id":"eb30ea4a-2ba2-4fec-b1ca-5a271897445e","year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.866601Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:8c806eb9ab66bd88f650dd2eef2d8f2f7aa4e1c0ddf3d25bd541bdf81aed951a","observation_id":"86bdae3d-73bd-41ba-949d-3492e6dcb0f3","resolution":{"observed_at":"2026-08-11T11:25:20.795744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.778425Z","title":"Meta-learning based few-shot link prediction for emerging knowledge graph,","venue":null,"work_id":"35acc353-b153-4c4c-80f0-99c8aaee6cda","year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.870820Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:813a74f7d99a5818b029b13c3e996376da0dde71ecf98f82df4463e67275097a","observation_id":"ef64a497-3a9c-45d8-9990-f59c1b2ecf95","resolution":{"observed_at":"2026-08-11T11:25:20.782994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.763385Z","title":"Heterogeneous graph trans- former,","venue":null,"work_id":"ba020abe-efdb-4ee6-b171-df06c1db8333","year":2020},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.875161Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:a312370b26f6ca32cf0624de2e92d43c1ef9f995d5f11ae5aea83f8fa5dbed7a","observation_id":"4e509a4d-d97e-414e-9b39-82bd25a05cee","resolution":{"observed_at":"2026-08-11T11:25:20.768053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.749342Z","title":"Modeling relational data with graph convolutional networks,","venue":null,"work_id":"73e3cb0f-6895-44c6-8b2a-fba14399a2ed","year":2018},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.879474Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:da856ffc4997009a32bad9bdd74343351d8e3f45257f65e98c80c8da9a41d33b","observation_id":"fa6bc6aa-a2ef-4850-93be-ff491c651aa8","resolution":{"observed_at":"2026-08-11T11:25:20.754190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.09679","last_updated":"2020-11-19T06:03:35Z","snapshot_observed_at":"2026-08-05T03:59:33.046010Z","submitted_at":"2020-11-19T06:03:35Z","title":"Scalable Graph Neural Networks for Heterogeneous Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.09679","snapshot_observed_at":"2026-08-11T11:25:19.883710Z","title":"Scalable graph neural networks for heterogeneous graphs,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.883710Z"},"links":{"cited_paper":"/paper/2011.09679","citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:eb37aa86905964936b4a12577d848a285a3a5cc32090b9df22a2422fe7dc6b01","observation_id":"95e42bfa-aa89-4a8c-a1ed-a725eeb3a4d5","resolution":{"observed_at":"2026-08-11T11:25:19.883710Z","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":"2026-08-11T11:25:20.734572Z","title":"Simple and efficient het- erogeneous graph neural network,","venue":null,"work_id":"58bd3038-0ad4-4fc7-bd11-7b825e8b4e66","year":2023},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.888614Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:e72dc26612945479df595cf7c57160f147c9179ab1d6531afe59fef14bf78a96","observation_id":"2a499469-931e-49d6-a0f4-e8505317c786","resolution":{"observed_at":"2026-08-11T11:25:20.739784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.719547Z","title":"Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes,","venue":null,"work_id":"faf688ab-b331-44d8-b730-6c049c70a1c7","year":2020},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.893073Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:da48e2cb512e19aa762a1cf7aafa20c7dfce702f835efdc9225715d57f77add9","observation_id":"b22007e1-8d5f-4c3e-9434-b0d83300f84e","resolution":{"observed_at":"2026-08-11T11:25:20.724252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.10097","last_updated":"2022-06-09T08:47:53Z","snapshot_observed_at":"2026-08-14T20:15:04.063387Z","submitted_at":"2021-08-23T11:56:20Z","title":"Graph Attention MLP with Reliable Label Utilization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.10097","snapshot_observed_at":"2026-08-11T11:25:19.897665Z","title":"Graph attention mlp with reliable label utilization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.897665Z"},"links":{"cited_paper":"/paper/2108.10097","citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:fe5c06b47a69a642aadde155feb0d50605fbb2f854e60a99bb4f74179c907174","observation_id":"e574ebdd-e950-48fa-ab13-f39e7e3bfad3","resolution":{"observed_at":"2026-08-11T11:25:19.897665Z","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":"2026-08-11T11:25:20.706337Z","title":"Random search and reproducibility for neural architecture search,","venue":null,"work_id":"47b389b7-6444-45c8-a0bd-4573f5a5bae6","year":2019},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.902484Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:cc76c4b01c13639745377a91fbea719f9f0cc7a605acce7c023af18783068d64","observation_id":"f476f4bf-12d6-468b-be16-3b93515c2080","resolution":{"observed_at":"2026-08-11T11:25:20.710362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.693581Z","title":"Heterogeneous graph sparsification for efficient representation learning,","venue":null,"work_id":"c95c2aaf-268c-4ab5-be61-0a71b271ca31","year":2022},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.906767Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:5ba4ef19294b00b71544383beafe8beffe9e547bbf6a0326d3a6a9f072e26383","observation_id":"7058bf2c-4544-41d7-b784-95945a5630fa","resolution":{"observed_at":"2026-08-11T11:25:20.697642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.680821Z","title":"Relation structure- aware heterogeneous graph neural network,","venue":null,"work_id":"b6b5ebcc-2490-4739-8559-04db0585aef5","year":2019},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.911048Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:97e91770eda44dc39c6bac30f286638f1f05135f350d2b144b7005276c008519","observation_id":"669360d0-11fe-4785-8292-87b76725ed2a","resolution":{"observed_at":"2026-08-11T11:25:20.684750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.667694Z","title":"Graph condensation for graph neural networks,","venue":null,"work_id":"8c47910c-e76b-44e4-ba68-d0b91d5d74f4","year":2022},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.914845Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:80c105c9d1e3241f9960a87bba3c6c41d9b57bdde5b005997f0f04d05dca3fc6","observation_id":"d9113fc3-85e8-4cfa-9540-f1320b496856","resolution":{"observed_at":"2026-08-11T11:25:20.672028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.11720","last_updated":"2025-01-27T09:40:25Z","snapshot_observed_at":"2026-08-13T08:01:56.733237Z","submitted_at":"2024-01-22T06:47:00Z","title":"Graph Condensation: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.11720","snapshot_observed_at":"2026-08-11T11:25:19.918646Z","title":"Graph condensation: A survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.918646Z"},"links":{"cited_paper":"/paper/2401.11720","citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:31c41dcdd07a8989ed8c93daf1eddb8e1c90ef67130da8ea9455743a75bafd36","observation_id":"a80fa71f-6401-4d89-8965-8a0b3deec7de","resolution":{"observed_at":"2026-08-11T11:25:19.918646Z","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":"2026-08-11T11:25:20.653750Z","title":"Heterogeneous graph condensation,","venue":null,"work_id":"166044e9-4aca-48d3-930e-c62950d5af95","year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.923154Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:64db72fa297598b0f8eebdb4779cc3d1bb1ea2885c13c897cd492bd1f3e00628","observation_id":"4bc3bddf-4e21-4abb-b8bf-439ba80bb5a8","resolution":{"observed_at":"2026-08-11T11:25:20.658632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.639882Z","title":"Arnetminer: extraction and mining of academic social networks,","venue":null,"work_id":"6100b5e6-312d-4ecb-838c-4c6ec057c051","year":2008},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.927300Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:f00966b609f92b01faedf2d9e44d03c879b9e3ce79f487ecae5ac2903dffea9a","observation_id":"95230a3b-bbf4-4818-8ac9-fa4e5b13fdfa","resolution":{"observed_at":"2026-08-11T11:25:20.644487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.625419Z","title":"Freebase: a collaboratively created graph database for structuring human knowledge,","venue":null,"work_id":"cd1a702f-6ae3-4931-9f1a-91d23e191606","year":2008},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.931365Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:218d3a442110219cf2a2371d1c1697f743485e4b096598e423882cf1ecbcfc96","observation_id":"8699147a-82d1-4715-ad24-2b87f4d5f25a","resolution":{"observed_at":"2026-08-11T11:25:20.630418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.611245Z","title":"metapath2vec: Scalable rep- resentation learning for heterogeneous networks,","venue":null,"work_id":"71c9625d-c1bf-44fa-a9ee-bb5be3fdcd34","year":2017},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.935356Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:bfbef0400f3a3b4eecffe4bac99e166b99b5b2f960f44c1acd6316da6038ade7","observation_id":"a85612c6-ca77-4a52-aa7f-6c10654a3c38","resolution":{"observed_at":"2026-08-11T11:25:20.616204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.598070Z","title":"MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding,","venue":null,"work_id":"3e414058-6d34-4074-adc9-a7c41ff6444d","year":2020},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.939310Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:84dee265d267113f95af255f7871fd8b850b7b830b3c4851e2fdf0cf4a834310","observation_id":"0108b796-650f-4544-9985-4344190fc844","resolution":{"observed_at":"2026-08-11T11:25:20.601977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03358","last_updated":"2024-06-29T13:07:00Z","snapshot_observed_at":"2026-08-14T10:07:31.700526Z","submitted_at":"2024-01-29T01:19:09Z","title":"A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03358","snapshot_observed_at":"2026-08-11T11:25:19.943143Z","title":"A comprehensive survey on graph reduction: Sparsification, coarsening, and condensation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.943143Z"},"links":{"cited_paper":"/paper/2402.03358","citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:7b4bf43395143a1b102581636257db5ab38afd7e989c770de8aca0329142e044","observation_id":"1e0fe11b-e71b-4bdb-b89a-b703c101f88c","resolution":{"observed_at":"2026-08-11T11:25:19.943143Z","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":"2026-08-11T11:25:20.584818Z","title":"Spectral sparsification of graphs,","venue":null,"work_id":"95d5289d-c5e0-4331-8db8-fcfe87068753","year":2011},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.947550Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:696fa9aa2a0ddabab9cf97c4fef9dbddabcd949962fe6bedbb6c86d3dd5bfaf9","observation_id":"2ca0e8ef-1228-43fb-9acb-c2db86533e2b","resolution":{"observed_at":"2026-08-11T11:25:20.589057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.571993Z","title":"A unified lottery ticket hypothesis for graph neural networks,","venue":null,"work_id":"283dd0fc-5b3b-49a1-831b-a8999f888094","year":2021},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.951571Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:1eca2800bf3d81ab9cdc3e13b74bc8de1d74b2b145520b5b69b1d1de54524073","observation_id":"94160450-81eb-462d-bbed-dbc45c19be03","resolution":{"observed_at":"2026-08-11T11:25:20.576084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.559526Z","title":"A novel graph oversampling framework for node classification in class-imbalanced graphs,","venue":null,"work_id":"47041300-3e22-49f6-a2e0-9ed669d2e6fa","year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.955476Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:dfb483bac8dcb3fddef7355e8de6ea9e86da2b6c2349a416e8614eaefff47e10","observation_id":"bf28a2ef-5bbe-4c92-b792-9453e96b003e","resolution":{"observed_at":"2026-08-11T11:25:20.563632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.545609Z","title":"Herding dynamical weights to learn,","venue":null,"work_id":"58e22799-638a-4a06-aabd-5dcf7eba8814","year":2009},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.959402Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:e62e214130686c660a4fc0d7ca58a1720f94bdeed7890ea99e5c7f651677d359","observation_id":"7821fb72-2f12-4fe2-b8b9-afc9ef3e4c41","resolution":{"observed_at":"2026-08-11T11:25:20.549961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.531771Z","title":"Facility location: concepts, models, algorithms and case studies. series: Contributions to management science,","venue":null,"work_id":"c3d2c67e-1e12-42d3-bd98-75c98ba1917b","year":2011},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.963545Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:9f22113d5510c88fe5a99ba6457f17ffc1ff589ec93237ffc37e609f218a0a83","observation_id":"166b2624-9ed4-4320-a984-c40312a4670c","resolution":{"observed_at":"2026-08-11T11:25:20.536433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.517600Z","title":"Active learning for convolutional neural networks: A core-set approach,","venue":null,"work_id":"75fee5f9-db76-48c3-a1cd-c91e440d0d66","year":2018},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.967711Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:4c743ffd1a3b967c10b25935e16489ba3754467cf052cf69f0b183d8b53ca5ea","observation_id":"d08daebd-8141-4bd4-9928-f7bd8d26a504","resolution":{"observed_at":"2026-08-11T11:25:20.522563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.502910Z","title":"Scaling up graph neural networks via graph coarsening,","venue":null,"work_id":"f3604597-49aa-41f2-a16d-f9d3c068bde0","year":2021},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.972015Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:237a20eaec48dcb47529e4398278240f287b0bb6a620173ab40d570bc44fa2b4","observation_id":"696f7662-dd7c-4c91-b521-0169963b5f72","resolution":{"observed_at":"2026-08-11T11:25:20.508418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.489308Z","title":"Condensing graphs via one-step gradient matching,","venue":null,"work_id":"ee9887c3-8e9e-4783-87b5-4232d6107ad0","year":2022},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.976185Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:54e30f6b8086e3b4c168f46cf9e27fcf7f1db5c290cacd5f323dd02af201d5f7","observation_id":"09a9b02e-d6e9-43d3-889b-1376190b0820","resolution":{"observed_at":"2026-08-11T11:25:20.493964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.475098Z","title":"Structure-free graph condensation: From large-scale graphs to con- densed graph-free data,","venue":null,"work_id":"4de63abb-44a5-452c-87b1-7c3f7773afb7","year":2023},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.981137Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:a75e3ab4f74bb4895fda06dab492b718da56cca2245938fab4c717f2463b06ff","observation_id":"b9de7a4e-2e93-4877-8754-cdca4bf9431f","resolution":{"observed_at":"2026-08-11T11:25:20.479722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.09202","last_updated":"2024-05-14T17:12:15Z","snapshot_observed_at":"2026-08-13T05:49:44.380866Z","submitted_at":"2023-10-13T15:48:12Z","title":"Graph Distillation with Eigenbasis Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.09202","snapshot_observed_at":"2026-08-11T11:25:19.985483Z","title":"Graph condensation via eigenbasis match- ing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.985483Z"},"links":{"cited_paper":"/paper/2310.09202","citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:555e39b922e468fa3b955b62bf8255a26bbc1e571ab73bcd0d3a6e16c3784dd7","observation_id":"53512564-4a71-4f5d-abfe-83c3946b9198","resolution":{"observed_at":"2026-08-11T11:25:19.985483Z","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":"2026-08-11T11:25:20.461739Z","title":"Graph-skeleton: ˜1% nodes are sufficient to represent billion-scale graph,","venue":null,"work_id":"ffae5859-67b5-4f38-b7b4-fa0db7e3a573","year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.990379Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:0b922d4987f9689581676e9e4e976a40e9b4e28394cf452b30cb9bb3beed7504","observation_id":"c4249eeb-e7ea-45d4-a59f-c8d1647a1cfa","resolution":{"observed_at":"2026-08-11T11:25:20.465909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.448985Z","title":"Graph condensation for open-world graph learning,","venue":null,"work_id":"64986543-ee57-485a-ad9c-3be205e77356","year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.994627Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:038ea9b66181046f485cc234e7ad7664f848f1e41d8da2eb5cfd0f095324f5c2","observation_id":"e11a30dd-68dc-44a6-88b0-35841eb0b79a","resolution":{"observed_at":"2026-08-11T11:25:20.453203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.13707","last_updated":"2025-01-23T08:49:04Z","snapshot_observed_at":"2026-08-14T09:37:08.975614Z","submitted_at":"2024-05-22T14:57:09Z","title":"Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.13707","snapshot_observed_at":"2026-08-11T11:25:19.999282Z","title":"Rethinking and accelerating graph condensation: A training- free approach with class partition,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:19.999282Z"},"links":{"cited_paper":"/paper/2405.13707","citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:752b4991a1cf0d685e2a4953037133a5587e4078106723a99635a1f9770c63e8","observation_id":"15dd57b1-ed24-4dbb-8da1-b4157f702751","resolution":{"observed_at":"2026-08-11T11:25:19.999282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.13200","last_updated":"2025-05-11T11:03:10Z","snapshot_observed_at":"2026-08-12T23:39:34.858792Z","submitted_at":"2024-06-19T04:14:57Z","title":"RobGC: Towards Robust Graph Condensation","version":2},"cited_work":{"arxiv_id":"2406.13200","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.13200","snapshot_observed_at":"2026-08-11T11:25:20.145770Z","title":"RobGC: Towards Robust Graph Condensation","venue":"cs.LG","work_id":"b023232f-4df4-4411-9c53-93affdb17fcd","year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.004179Z"},"links":{"cited_paper":"/paper/2406.13200","citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:b8207567dcfaa579f92e237ea93d93c92c3fd53447c674fa94d13dcd88e3200a","observation_id":"a869a098-6db4-49cb-9d9a-bde04796dca4","resolution":{"observed_at":"2026-08-11T11:25:20.152531Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.13697","last_updated":"2022-06-28T02:10:05Z","snapshot_observed_at":"2026-08-14T19:01:07.836950Z","submitted_at":"2022-06-28T02:10:05Z","title":"Graph Condensation via Receptive Field Distribution Matching","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.13697","snapshot_observed_at":"2026-08-11T11:25:20.008913Z","title":"Graph condensation via receptive field distribution matching,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.008913Z"},"links":{"cited_paper":"/paper/2206.13697","citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:84f9706b25a9b2375a2b2b75f81cfa7d3d53a78b53dd4a4ef80a19325cce885e","observation_id":"8ba5b6f8-4903-4c5b-b08f-b0eabf8caa53","resolution":{"observed_at":"2026-08-11T11:25:20.008913Z","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":"2026-08-11T11:25:20.435902Z","title":"Graph distillation with eigenbasis matching,","venue":null,"work_id":"196a235b-34c9-432a-8218-3360539a7fba","year":2024},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.014411Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:0477ba4d0934e2bcacc9cece9493932bed7c9899bb09cee9f199d5a8f838ebf9","observation_id":"efa2ae9e-ef2b-4669-b381-2aaccdf1f07e","resolution":{"observed_at":"2026-08-11T11:25:20.440090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.421888Z","title":"Maximizing the spread of influence through a social network,","venue":null,"work_id":"d88a18ce-5e9f-4e4f-9df0-82bbc5b43604","year":2003},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.020887Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:a7e5c66328b95a19dbc963a695edf979ec9d45261f42c578aba8413bf05072c0","observation_id":"2b9b90fd-2694-4002-b19c-ab34db508ee6","resolution":{"observed_at":"2026-08-11T11:25:20.426307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.407068Z","title":"Maximizing the spread of influence through a social network,","venue":null,"work_id":"20e2f954-ac56-42b6-9aa8-8812b034feba","year":2003},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.026018Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:118fe0acfd5b71eb991d2ad7d7e1d5c8815a8631adc23688127f09e834d42685","observation_id":"d406c096-d62f-4110-8377-27aa68c6a0f2","resolution":{"observed_at":"2026-08-11T11:25:20.412558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.392201Z","title":"An analysis of approximations for maximizing submodular set functions - I,","venue":null,"work_id":"b6447e64-4edf-4ab9-a92d-6281597a00dd","year":1978},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.030734Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:da2face42a668b037ee77b7800e607806eba57f3e69f53d2dd85d2ba192282fe","observation_id":"dc59460a-df4a-44b0-a211-6a68c1366f84","resolution":{"observed_at":"2026-08-11T11:25:20.396938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.377293Z","title":"Scalable and parallelizable influence maximization with random walk ranking and rank merge pruning,","venue":null,"work_id":"ed102415-f038-4b77-a263-278e68d4d66b","year":2017},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.035569Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:6fcefda97acf8a5a3218af999d722bfcaa0a26d07a140380a1e866adf78a459c","observation_id":"2b396534-58ac-4eb0-a033-b541834a1f41","resolution":{"observed_at":"2026-08-11T11:25:20.382076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.362593Z","title":"Comparing sets of patterns with the jaccard index,","venue":null,"work_id":"bb09dd0a-7f10-45ea-a2ee-db68d3bddffc","year":2018},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.040208Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:b3df80d2741f23763ef28728318469819b19b1c71319698e5b82eea15c000eb6","observation_id":"d88c076f-27a0-430e-ad28-770c4f271231","resolution":{"observed_at":"2026-08-11T11:25:20.367289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.348495Z","title":"The lov ´asz hinge: A novel convex surrogate for submodular losses,","venue":null,"work_id":"327beb79-fce8-47b4-83bd-784bc6f4e512","year":2020},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.044579Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:f77485e98a098028093a5f4f165e38b95dea3d9329ce587c422dd5347bf4708b","observation_id":"ef093b9a-d091-4968-8ce8-c724b7bcff8f","resolution":{"observed_at":"2026-08-11T11:25:20.353104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.333540Z","title":"The lov ´asz-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks,","venue":null,"work_id":"7df6bcd9-e77b-451b-a1b1-0fbfa4d58c1b","year":2018},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.049053Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:a6d9413e6bef9abaa4576dcb2e84df80440c6a9bb5df159f942f2efdcbad1c98","observation_id":"96a5ff07-0746-4caa-82b6-944b15c365d5","resolution":{"observed_at":"2026-08-11T11:25:20.338503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.318980Z","title":"A class of submodular functions for document summarization,","venue":null,"work_id":"cdd8d286-9601-4372-87cd-ce566d8aa45b","year":2011},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.053277Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:27e16fbf34c9db4aa35d28f28a473f68cc3a96dbe3b89ff253cdad5ee365478f","observation_id":"e53f0490-0d8a-4cbd-82c1-702bd0360f33","resolution":{"observed_at":"2026-08-11T11:25:20.323367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.305271Z","title":"Scaling graph neural networks with approximate pagerank,","venue":null,"work_id":"3ccfe2c6-9b7b-49cf-ae06-6bcd687308ef","year":2020},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.057299Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:77eecdd0ddd36609d972459a563cabb1ff77673d6d2056be082ca77e635afd2a","observation_id":"c56309dc-33eb-4f7b-9ddd-07eef7d5419b","resolution":{"observed_at":"2026-08-11T11:25:20.309490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.290864Z","title":"Degree centrality, betweenness centrality, and closeness centrality in social network,","venue":null,"work_id":"20634b72-16d6-437a-b0ba-906b8e059665","year":2017},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.061889Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:960be1c9c4d4396f818506ff07069b3d87befe4534bd84b333dd1a498d2dd66b","observation_id":"5f5dad2f-aba7-4b19-8a6a-3f9d263ea761","resolution":{"observed_at":"2026-08-11T11:25:20.295853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.276541Z","title":"Hubs, authorities, and communities,","venue":null,"work_id":"721ab0c2-4caf-4773-ba99-db31aaf3196f","year":1999},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.065798Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:500357367087e237c61162872318de46c976d3265620b16e6005f5a51a6cdf88","observation_id":"94a9971e-ff4b-48db-a994-9c5206e760b3","resolution":{"observed_at":"2026-08-11T11:25:20.281095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.01315","last_updated":"2020-08-25T15:46:13Z","snapshot_observed_at":"2026-07-06T08:18:46.549511Z","submitted_at":"2019-09-03T17:10:28Z","title":"Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.01315","snapshot_observed_at":"2026-08-11T11:25:20.069906Z","title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks,","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.069906Z"},"links":{"cited_paper":"/paper/1909.01315","citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:9a33be0f02b5db25b11424a847032608bbc7ebcf190f655d52ca42dbd65ebd99","observation_id":"5f56e5a7-fdaf-49c5-a5e1-43d6697f2e6f","resolution":{"observed_at":"2026-08-11T11:25:20.069906Z","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":"2026-08-11T11:25:20.261291Z","title":"A collection of benchmark datasets for systematic evaluations of machine learning on the semantic web,","venue":null,"work_id":"7332ded3-21ac-459d-b595-ce3451a7ece6","year":2016},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.074064Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:6c36ca0529f9e436abb48eda2aea6de2ebf4d7bfa9f2b85f6dee120be12f3764","observation_id":"e92e4a61-a284-4ba2-86d1-455101b748f1","resolution":{"observed_at":"2026-08-11T11:25:20.266355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T11:25:20.078135Z","title":"Visualizing data using t-sne","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T11:25:20.078135Z"},"links":{"citing_paper":"/paper/2412.16250"},"observation_digest":"sha256:15f63c3fc1db7130b7e3eb8fbd667da642fa5b068a6475dadcb4bf1c893af861","observation_id":"dcab42f6-0671-4ef2-8d8f-bf2dbdf55ec0","resolution":{"observed_at":"2026-08-11T11:25:20.078135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.16250","last_updated":"2024-12-20T02:49:32Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T10:07:41.692459Z","submitted_at":"2024-12-20T02:49:32Z","title":"Training-free Heterogeneous Graph Condensation via Data Selection"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":1,"verified_fuzzy":51},"total_outbound_references":61},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 0 inbound Pith citation observations for arXiv:2412.16250."}