{"as_of":"2026-08-10T12:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:42df77d43b0e8e066dd0349dc02a30f483a0cb83b7b24c7e2274c2315221896d","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T06:04:17.378893Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.06157/citation-record","integrity":"/paper/2506.06157/integrity","json":"/paper/2506.06157/citation-record.json","paper":"/paper/2506.06157"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T06:04:11.720853Z","title":"L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:11.720853Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:1028de830d4a926f35371e0f8fb7535f29ae9d2197d8be76df0f96909810a097","observation_id":"ad6eb98d-8d0b-480c-bcdc-6e1d1d00da27","resolution":{"observed_at":"2026-08-07T06:04:11.720853Z","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":"2026-08-07T06:04:24.487917Z","title":"Graph markup language (graphml)","venue":null,"work_id":"0387b3fe-d655-4d79-96a8-38014612fa11","year":2013},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:11.859420Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:1f973bc8bbcdb89f0217d5386d0aa5e78a2d24dd8b4b77d1f730f329ad6a78fb","observation_id":"664b7213-7a60-4590-a29a-636d1bbb47fa","resolution":{"observed_at":"2026-08-07T06:04:24.656007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:24.139517Z","title":"D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al","venue":null,"work_id":"1f633b56-6696-4185-9803-39abfc20cd0d","year":1901},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:12.067032Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:15134c9704e419932c6ecb2b871fde39be1913328abca982646995ac086445b5","observation_id":"db1be566-bd7c-497c-85ba-9a1257929c18","resolution":{"observed_at":"2026-08-07T06:04:24.313068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:23.860987Z","title":"Lmbot: distilling graph knowledge into language model for graph-less deployment in twitter bot detection","venue":null,"work_id":"f33e3b12-c72d-45f8-96e4-42e984f8ca95","year":2024},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:12.206233Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:4ebaf69c419018f6f73cec0f4d8bae559c27429425937497d64bad374b5e91e2","observation_id":"2898b609-1160-4732-9b2d-f17b598a0e59","resolution":{"observed_at":"2026-08-07T06:04:24.032214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05845","last_updated":"2023-10-09T16:42:00Z","snapshot_observed_at":"2026-08-05T15:33:31.680807Z","submitted_at":"2023-10-09T16:42:00Z","title":"GraphLLM: Boosting Graph Reasoning Ability of Large Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05845","snapshot_observed_at":"2026-08-07T06:04:12.306341Z","title":"Graphllm: Boosting graph reasoning ability of large language model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:12.306341Z"},"links":{"cited_paper":"/paper/2310.05845","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:32fbee2cb0b43037ef275fc24337bfb0b79aa9c2a89d6c2f4c5484cfeac156e2","observation_id":"06a8f34c-d885-46b5-a80f-36496bf3bbc3","resolution":{"observed_at":"2026-08-07T06:04:12.306341Z","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":"2026-08-07T06:04:23.626211Z","title":"Heterogeneous graph contrastive learning for recommendation","venue":null,"work_id":"f846462d-ae50-446b-a8e8-df43cfebbc07","year":2023},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:12.506433Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:5d0585c3276f3c70d4e7781f3b02b4e7e2575679655c31e8c407b91295dc7d0c","observation_id":"e983ba50-91ab-4213-be51-42dff174a4a4","resolution":{"observed_at":"2026-08-07T06:04:23.705023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"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":"2026-08-07T06:04:12.654691Z","title":"Llaga: Large language and graph assistant","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:12.654691Z"},"links":{"cited_paper":"/paper/2402.08170","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:dc2e8ac09c60ee0115a499846f454dd49d3e37fc395fefd0a312d263938c1337","observation_id":"01e108d0-e4e5-4219-8a7d-03de13845e2c","resolution":{"observed_at":"2026-08-07T06:04:12.654691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-07T06:04:12.846933Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:12.846933Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:b28e0db5900576627737def00f3c2f652e7d01543a0b34dc3b65ce9978a1fbaa","observation_id":"bd066ee8-2383-4b0a-a53d-a24345d86082","resolution":{"observed_at":"2026-08-07T06:04:12.846933Z","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":"2026-08-07T06:04:23.332323Z","title":"V ., and Swami, A","venue":null,"work_id":"9e990f05-c86b-4332-bebf-4831f9ad1279","year":2017},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:13.008375Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:20e508f3a1f3aab3b2067f2ee25ea6c6f5773aa9fc5034beb2f97d84fc0d3a2c","observation_id":"b0247295-f74b-49cc-8009-6fd38c922424","resolution":{"observed_at":"2026-08-07T06:04:23.452703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.02428","last_updated":"2019-04-25T10:06:09Z","snapshot_observed_at":"2026-08-02T18:54:43.326912Z","submitted_at":"2019-03-06T14:50:02Z","title":"Fast Graph Representation Learning with PyTorch Geometric","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.02428","snapshot_observed_at":"2026-08-07T06:04:13.113175Z","title":"and Lenssen, J","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:13.113175Z"},"links":{"cited_paper":"/paper/1903.02428","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:d578d3d0d7df2f5472a35e69a8accc9b4f7efb9726c60db40ad12ff8d305ee01","observation_id":"1feabc73-e757-4beb-ac08-d4e02f66d1b6","resolution":{"observed_at":"2026-08-07T06:04:13.113175Z","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":"2026-08-07T06:04:23.107149Z","title":"Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding","venue":null,"work_id":"3ca3e93d-1b21-467c-9038-0c851b2ddeff","year":2020},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:13.256248Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:7cb3c4bbb682a4053d9f64b33ebcac1ec748f9b40f8a028cf264b1d618ded5d1","observation_id":"8991bb65-da53-47c8-8c9e-c9acc76ccbf7","resolution":{"observed_at":"2026-08-07T06:04:23.214437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:22.976654Z","title":"Gml: A portable graph file format","venue":null,"work_id":"17950b65-34ba-4f33-b1c8-b1fca150b831","year":1997},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:13.395829Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:b9604977e5a6e2bd7e7606dd7411ae90ffa5fb19cc5246f1ed7f6976206d4cda","observation_id":"c95c33cf-a191-470d-99c2-544c8c1ac25d","resolution":{"observed_at":"2026-08-07T06:04:23.044166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-07T06:04:13.523647Z","title":"J., Shen, Y ., Wallis, P., Allen-Zhu, Z., Li, Y ., Wang, S., Wang, L., and Chen, W","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:13.523647Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:c81bb40b2442ec2368255a286a7875a956989040d325fc5f4f6380711a868d2b","observation_id":"ff319034-c37f-418d-9df0-55161b53836e","resolution":{"observed_at":"2026-08-07T06:04:13.523647Z","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":"2026-08-07T06:04:22.811232Z","title":"Gpt-gnn: Generative pre-training of graph neural networks","venue":null,"work_id":"0968a31a-f527-4358-8521-6c28aa9b1630","year":2020},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:13.640976Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:fd94eff75bab91686377ff0a429ae1da447a8f7fe792ede2f1c540fce831cdf1","observation_id":"ed8d495e-a568-485d-b56f-b3a12cd4ab07","resolution":{"observed_at":"2026-08-07T06:04:22.869128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:22.654730Z","title":"Heterogeneous graph transformer","venue":null,"work_id":"5cc241f0-d962-4ed7-9e5b-5de41886d0b8","year":2020},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:13.791740Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:28da3b77fafadb40a927f382a78d5e3a0f4b72bd361555c906dacf70c5a57952","observation_id":"a809e76c-c36c-4765-97eb-f68feae38cfe","resolution":{"observed_at":"2026-08-07T06:04:22.714767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:22.480251Z","title":"Pre-training on large-scale heterogeneous graph","venue":null,"work_id":"9cae34a8-6297-4aa0-9989-e4d92e25a18e","year":2021},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:13.916008Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:1d6a3ed048696e4d08bcbc85b085ca29e6e0b1eb192a7340c89448e645f6e0b2","observation_id":"4a56b4d5-7ca3-4e1f-a3c8-ed0b6ee972c5","resolution":{"observed_at":"2026-08-07T06:04:22.570652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:22.320111Z","title":"X., and Li, J","venue":null,"work_id":"086b3f33-2b0f-44f4-b438-7d629ed1fe21","year":2024},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:14.064465Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:45e3b39234db2ca1becd40f1af3fa26b424ec3da7679586e55cfdf2f20b9d9ce","observation_id":"081f123d-e31f-4da4-bbe6-43f1498b2219","resolution":{"observed_at":"2026-08-07T06:04:22.398684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.14961","last_updated":"2024-10-19T03:27:19Z","snapshot_observed_at":"2026-07-06T19:36:19.567469Z","submitted_at":"2024-10-19T03:27:19Z","title":"LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.14961","snapshot_observed_at":"2026-08-07T06:04:14.191133Z","title":"Langgfm: A large language model alone can be a powerful graph foundation model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:14.191133Z"},"links":{"cited_paper":"/paper/2410.14961","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:319296c598741e77c7ef1a73a501d7abc68766a4bfcabdbffcf724229afcc9a4","observation_id":"b3428b61-e21d-4168-a2a4-ebcf997720f1","resolution":{"observed_at":"2026-08-07T06:04:14.191133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00149","last_updated":"2024-07-12T23:01:32Z","snapshot_observed_at":"2026-07-06T16:25:46.699214Z","submitted_at":"2023-09-29T21:15:26Z","title":"One for All: Towards Training One Graph Model for All Classification Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00149","snapshot_observed_at":"2026-08-07T06:04:14.300110Z","title":"One for all: Towards training one graph model for all classification tasks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:14.300110Z"},"links":{"cited_paper":"/paper/2310.00149","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:aaccb38583cd9812a4f2908fb6d431e3656e20bf21474f68ac55913d9dd71404","observation_id":"0a058a99-bfd4-4e91-89ec-244273713cb2","resolution":{"observed_at":"2026-08-07T06:04:14.300110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11829","last_updated":"2025-03-10T16:14:30Z","snapshot_observed_at":"2026-07-06T16:34:54.717394Z","submitted_at":"2023-10-18T09:31:21Z","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11829","snapshot_observed_at":"2026-08-07T06:04:14.422754Z","title":"S., et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:14.422754Z"},"links":{"cited_paper":"/paper/2310.11829","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:3422967c35ede562a98781a0c19d770981ca7f2b3dc1c09544f92a4b50fca4fe","observation_id":"afab44a1-1e26-40b8-900d-afe9420f714e","resolution":{"observed_at":"2026-08-07T06:04:14.422754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-07T06:04:14.539396Z","title":"Roberta: A robustly optimized bert pretraining approach.arXiv preprint arXiv:1907.11692, 364, 2019","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:14.539396Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:f3141316111f1a6e45f4467f7ca63f48439af7eeb55058b9934cd0a8edf121cc","observation_id":"d4e813f1-3c5f-4118-ba7a-89805474ede5","resolution":{"observed_at":"2026-08-07T06:04:14.539396Z","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":"2026-08-07T06:04:22.116983Z","title":null,"venue":null,"work_id":"02d2e3dd-661a-4652-a213-4c011f94b13a","year":2024},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:14.631979Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:26361b6d81d1b2324a8a534dc6d9d144d48c1cebf2e1b098d7838f9273ea4fff","observation_id":"5fbf0ee5-321a-4283-92c5-7de099c17da4","resolution":{"observed_at":"2026-08-07T06:04:22.246081Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-07T06:04:14.737520Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:14.737520Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:4d2accd1e3f17345120209dd072de541a87279341a26fc7bf57e584e858dd36d","observation_id":"d21e02b2-d09a-4c73-b686-216d01c95c6c","resolution":{"observed_at":"2026-08-07T06:04:14.737520Z","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":"2026-08-07T06:04:21.987814Z","title":"Relation structure-aware heterogeneous information network embedding","venue":null,"work_id":"a8a7108e-de93-43f1-a22d-a49df4bccb11","year":2019},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:14.873719Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:7cf3e5f5cc4399025044dd8e727dc4831fce2700206792b4851058caab99d5be","observation_id":"a33d7a6d-6dad-4408-b70a-03a36bfed889","resolution":{"observed_at":"2026-08-07T06:04:22.052602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:21.834020Z","title":"Single- cell biological network inference using a heterogeneous graph transformer","venue":null,"work_id":"a32e603e-5f32-493f-be59-27cdddad780b","year":2023},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:14.995337Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:9cfb000d87d6ff1d266dde99bd63cef0fa101f464b2104275d9277a2de371a34","observation_id":"858ecbc0-090e-41d7-a241-ffc682b82155","resolution":{"observed_at":"2026-08-07T06:04:21.914783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:15.151480Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:15.151480Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:9dc39b1f14288e502e54df460cb0fda1cdc320969b90ecb55a8fe17219f28aa4","observation_id":"53aff4df-0511-4a15-bec4-d74dbaf0e0d4","resolution":{"observed_at":"2026-08-07T06:04:15.151480Z","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":"2026-08-07T06:04:21.656036Z","title":"Scikit-learn: Machine learning in python.the Journal of machine Learning research, 12:2825–2830, 2011","venue":null,"work_id":"3b7478ee-d260-41a2-9e8c-4ef0de982361","year":2011},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:15.275838Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:c5271f7c76760f3de3b471c9bc23770127600ce5c72dab61ab4065e60c7344a6","observation_id":"d5fdf1c2-7772-4309-b85d-f321323b0f35","resolution":{"observed_at":"2026-08-07T06:04:21.722092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-08-07T06:04:15.418693Z","title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:15.418693Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:b0b7922dedb586c16e78e265409bf71801718b9c241acaa9bafb11205eeb4d9d","observation_id":"a8e4c835-ec85-41c0-bb32-038ed60b3216","resolution":{"observed_at":"2026-08-07T06:04:15.418693Z","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":"2026-08-07T06:04:21.482831Z","title":"N., Bloem, P., Van Den Berg, R., Titov, I., and Welling, M","venue":null,"work_id":"939cfc58-e2b0-4b91-8256-c582d00ef210","year":2018},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:15.529094Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:2a021735ee2ac818229e41c20edba1c965e1e82a13336fe812af686598ab63b4","observation_id":"f89961fa-bc01-4f46-94f4-8dbbd58ac524","resolution":{"observed_at":"2026-08-07T06:04:21.576653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.10197","last_updated":"2019-02-26T20:15:09Z","snapshot_observed_at":"2026-08-06T13:43:56.202740Z","submitted_at":"2019-02-26T20:15:09Z","title":"RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.10197","snapshot_observed_at":"2026-08-07T06:04:15.630932Z","title":"Rotate: Knowledge graph embedding by relational rotation in complex space","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:15.630932Z"},"links":{"cited_paper":"/paper/1902.10197","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:4c2cba8e2d964174adb1b44d3cf9cbc7ae8fa90825248ee4c62356f8e87fa2ba","observation_id":"e5c2e98f-31c8-4ae2-83d4-5860477a229e","resolution":{"observed_at":"2026-08-07T06:04:15.630932Z","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":"2026-08-07T06:04:21.311839Z","title":"Walklm: A uniform language model fine-tuning framework for attributed graph embedding","venue":null,"work_id":"ceb9c571-6652-45a4-a437-7816c550d4ad","year":2024},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:15.751573Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:cbe9da52947e894e691fbac653d8499a432dc848ef94dd96e335e7dc96c24108","observation_id":"6b5f4977-a5b2-4611-9cbe-5ef50274f7c2","resolution":{"observed_at":"2026-08-07T06:04:21.382439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:21.062057Z","title":"Graphgpt: Graph instruction tuning for large language models","venue":null,"work_id":"dc5ea971-4d76-4359-b7f5-956da14d3a76","year":2024},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:15.921095Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:2f9db63c50dea13235ed67a24ca321230130ca5da61c3fe069d2c60d2e7a4f09","observation_id":"c1f6a188-fc0b-46ca-9f88-6d4e400d3487","resolution":{"observed_at":"2026-08-07T06:04:21.203887Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:20.759749Z","title":"Higpt: Heterogeneous graph language model","venue":null,"work_id":"63676a70-5d12-4a97-a8e1-d20d20a386d7","year":2024},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.012048Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:771462c4da6b26119be02d345b9c7750f990d620319f20368ea01c1a64094cc4","observation_id":"b0530591-94a0-49c2-9858-b7d5350c9994","resolution":{"observed_at":"2026-08-07T06:04:20.910741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:20.373981Z","title":null,"venue":null,"work_id":"d869d0a0-ba39-46fd-95ce-d131d7694ed6","year":2023},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.121944Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:24fe6a13364ade530d377ebcbe3ee9ee73344232b759372d73e137c26d312205","observation_id":"48380e5b-95cb-4496-bfe6-8a547d1499a3","resolution":{"observed_at":"2026-08-07T06:04:20.537697Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T06:04:16.248050Z","title":"Llama: open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.248050Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:b37421178b18a50814612bd431bba56dcdcf9bddbd2b5652f4743f1dd8f14d91","observation_id":"d26f3c8c-449c-4d3a-897d-7da215acd7fe","resolution":{"observed_at":"2026-08-07T06:04:16.248050Z","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":"2026-08-07T06:04:20.080080Z","title":"Can language models solve graph problems in natural language? Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"db98747f-ee05-4331-9763-b25d57c3b1b9","year":2024},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.312641Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:38d48d7df0b52b14e76b0d8561f44c92c6d23714c08b57f9177152e88f966659","observation_id":"efd70c6a-14f9-4542-989f-a0c484b12d07","resolution":{"observed_at":"2026-08-07T06:04:20.205072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"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":"2026-08-07T06:04:16.383986Z","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":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.383986Z"},"links":{"cited_paper":"/paper/1909.01315","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:4b6a46b01cf9b0835da2d710316be8d4f80b729bb92c405366097d7ef8d4fa3c","observation_id":"0b47e632-bcf1-49a5-ba95-04957683d64c","resolution":{"observed_at":"2026-08-07T06:04:16.383986Z","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":"2026-08-07T06:04:19.783996Z","title":null,"venue":null,"work_id":"98a19998-45e2-4623-936e-91aa9e2c2946","year":2022},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.484756Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:ee6a3993cd5401fc19b060fac3e4630f0cda23509860b7c45f4a221fea2a2244","observation_id":"c4d25ad3-22ee-4d7b-a0e3-2b9851dcf8f4","resolution":{"observed_at":"2026-08-07T06:04:19.934106Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:19.486788Z","title":"Self-supervised heterogeneous graph neural network with co- contrastive learning","venue":null,"work_id":"0af967b9-8466-4c1d-82cc-9fbe23e059c0","year":2021},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.545661Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:234a000676d3a314eca5aa65bbd21eb7683b9db2cac9ced235a95c3ec5eb8527","observation_id":"4442dc53-75ff-4a5f-ac1b-a9ca4cc1bcaa","resolution":{"observed_at":"2026-08-07T06:04:19.630302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:19.086589Z","title":null,"venue":null,"work_id":"ae18dfa7-2620-4ea4-8f74-92fbb8988d34","year":2022},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.623198Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:94d3cf904e6d4450fa3cd18ab6d9551a44b99df90e7c26716e41b3b649eb8ae7","observation_id":"13a7926d-6a12-4839-a01c-ce821c6b7f3a","resolution":{"observed_at":"2026-08-07T06:04:19.259932Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:18.680103Z","title":"Transformers: State-of-the-art natural language processing","venue":null,"work_id":"344a3498-35db-4333-a0d0-02bb5de92393","year":2020},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.710437Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:20b88810b862f80561e740e41d01d15319c5c8936a3575a6f527abf9b90c35bd","observation_id":"be39b3ef-dd10-4200-9f47-f9c7f558031e","resolution":{"observed_at":"2026-08-07T06:04:18.879195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-07T06:04:16.776361Z","title":"Qwen3 technical report","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.776361Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:404dac1bb9d899131c860ce00f6272c91dc42033feda71ef93f6f6b2df412496","observation_id":"c10f6d60-0e90-4c96-8b3e-38fab55ec22e","resolution":{"observed_at":"2026-08-07T06:04:16.776361Z","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":"2026-08-07T06:04:18.402777Z","title":"Heterogeneous network representation learning: A unified framework with survey and benchmark","venue":null,"work_id":"cd3da320-813a-4ddd-bff9-12962dfd69ce","year":2020},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.844490Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:d78cd68eef2ccb749476efe07ed5a7f473105b9e4270afb269431da00c1323ec","observation_id":"ff292f52-685f-4764-942b-8fd4f0c5dfe0","resolution":{"observed_at":"2026-08-07T06:04:18.531174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:18.179788Z","title":"Interpretable and efficient heterogeneous graph convolutional network","venue":null,"work_id":"11a4453f-0f6f-4d47-a5dc-e4af0a43ec0b","year":2021},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:16.918676Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:d5f6468fc42e1227ad7c39c24359059ad7c6188a82db61b03edd83bf9154d0e1","observation_id":"e1e3fc63-6743-462f-a008-931cc8cc9596","resolution":{"observed_at":"2026-08-07T06:04:18.286341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:18.031893Z","title":"Self-supervised heterogeneous graph pre-training based on structural clustering","venue":null,"work_id":"abe39aaf-b649-438e-9fae-25fc7b62d087","year":2022},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:17.021880Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:ef316fc247fa8325b05b1b2b408b614003279712cb56a1a3f2d9e8bc319759c7","observation_id":"fc2e0879-6c9f-4447-99c0-8829e4cc30a0","resolution":{"observed_at":"2026-08-07T06:04:18.089102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.07134","last_updated":"2024-02-06T03:08:44Z","snapshot_observed_at":"2026-07-06T16:05:58.986548Z","submitted_at":"2023-08-14T13:41:09Z","title":"Language is All a Graph Needs","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.07134","snapshot_observed_at":"2026-08-07T06:04:17.194313Z","title":"Natural language is all a graph needs.arXiv preprint arXiv:2308.07134, 4(5):7, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:17.194313Z"},"links":{"cited_paper":"/paper/2308.07134","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:bd23583f29229e4433c80632f666b1d1be5e539fbed6672dc55d87d918d568db","observation_id":"cc088158-b27e-45fe-980d-b54d14bfdd18","resolution":{"observed_at":"2026-08-07T06:04:17.194313Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.00935","last_updated":"2024-07-01T03:35:59Z","snapshot_observed_at":"2026-08-08T14:16:21.405979Z","submitted_at":"2024-07-01T03:35:59Z","title":"Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining","version":1},"cited_work":{"arxiv_id":"2407.00935","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.00935","snapshot_observed_at":"2026-08-07T06:04:17.766182Z","title":"Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining","venue":"cs.LG","work_id":"8eb1ca25-4396-4a23-90f1-12a260552ac1","year":2024},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:17.299617Z"},"links":{"cited_paper":"/paper/2407.00935","citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:bff54ebf2a3104934074bf3b6261795b369871aecb84be9e84e433be5a4b1594","observation_id":"743caa6b-568e-4984-ad77-44456a33f396","resolution":{"observed_at":"2026-08-07T06:04:17.824261Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"1940.50470","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:17.502119Z","title":"Llm as gnn: Graph vocabulary learning for graph foundation model","venue":null,"work_id":"d883c848-5e5c-4496-a238-d85e265a44a7","year":1997},"citing_paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:17.378893Z"},"links":{"citing_paper":"/paper/2506.06157"},"observation_digest":"sha256:ef09805c4d062e5d6cdd3376e073a450f0caa850a4a1e34522c2ec4ba23b3464","observation_id":"1907663f-0d2f-476e-a7fa-bb58505a5455","resolution":{"observed_at":"2026-08-07T06:04:17.608938Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.06157","last_updated":"2025-07-30T03:58:06Z","latest_version":2,"primary_category":"cs.SI","snapshot_observed_at":"2026-08-10T08:35:52.378297Z","submitted_at":"2025-06-06T15:21:24Z","title":"Masked Language Models are Good Heterogeneous Graph Generalizers"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":2,"verified_fuzzy":24},"total_outbound_references":48},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2506.06157."}