{"as_of":"2026-08-16T21:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1cc40bada4b90e9ec7137a32037ca59bc743139e19e5a2df23c12de016dfa9a2","coverage":[{"denominator":95,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":95,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:44:53.396903Z","state":"measured"},{"denominator":95,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":95,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2506.07168/citation-record","integrity":"/paper/2506.07168/integrity","json":"/paper/2506.07168/citation-record.json","paper":"/paper/2506.07168"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.103551Z","title":"Friends and neighbors on the web.Social networks, 25(3):211– 230, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.103551Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:62069937e0ade0ec80e6ec2f900b77afe2e6069868562607991d8e8df72dc67b","observation_id":"82834647-2295-4ffd-8e44-440662fd783e","resolution":{"observed_at":"2026-08-07T05:44:53.103551Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.09367","last_updated":"2018-08-28T15:38:41Z","snapshot_observed_at":"2026-08-14T18:36:07.753608Z","submitted_at":"2018-08-28T15:38:41Z","title":"Deriving Machine Attention from Human Rationales","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.09367","snapshot_observed_at":"2026-08-07T05:44:53.107643Z","title":"Deriving machine attention from human rationales","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.107643Z"},"links":{"cited_paper":"/paper/1808.09367","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:d790c9ef1c7871357aa0bf780f5e479c10cfd388da96edbf72a5efcc727be940","observation_id":"2c8a604d-12a1-48c1-bb5d-18192c585144","resolution":{"observed_at":"2026-08-07T05:44:53.107643Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.111465Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.111465Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:87b45f45ba92c56627ab5c76c0042ec86cfc038c15982ad6017311e97885e742","observation_id":"6b350226-f1c4-4f52-b67d-365abb9e0b21","resolution":{"observed_at":"2026-08-07T05:44:53.111465Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.05085","last_updated":"2017-05-15T06:49:04Z","snapshot_observed_at":"2026-08-14T21:00:46.179080Z","submitted_at":"2017-05-15T06:49:04Z","title":"Active Learning for Graph Embedding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.05085","snapshot_observed_at":"2026-08-07T05:44:53.114662Z","title":"Active learning for graph embedding","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.114662Z"},"links":{"cited_paper":"/paper/1705.05085","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:d4d6d4f6571bd1e354f7a8bad7859f1614fe3de82c3ac7f565d1307b86509d84","observation_id":"ac08d11e-916f-4ad6-a441-077a4c3e2ec7","resolution":{"observed_at":"2026-08-07T05:44:53.114662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05845","last_updated":"2023-10-09T16:42:00Z","snapshot_observed_at":"2026-08-16T14:53:45.330716Z","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":"2026-08-07T05:44:53.118146Z","title":"Graphllm: Boosting graph reasoning ability of large language model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.118146Z"},"links":{"cited_paper":"/paper/2310.05845","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:0ec38752f10e29714f47acfe3828c22bfc80b2830149ae5d4f53dde66c738e4a","observation_id":"6f87505a-226a-4a78-9542-ad84e140965a","resolution":{"observed_at":"2026-08-07T05:44:53.118146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.15486","last_updated":"2023-05-02T14:46:04Z","snapshot_observed_at":"2026-08-16T16:27:50.242339Z","submitted_at":"2022-09-30T14:20:07Z","title":"Graph Neural Networks for Link Prediction with Subgraph Sketching","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.15486","snapshot_observed_at":"2026-08-07T05:44:53.121625Z","title":"Graph neural networks for link prediction with subgraph sketching","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.121625Z"},"links":{"cited_paper":"/paper/2209.15486","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:258feb520699ed40c542957ba866e729926d4a14a6b4e13307043176ed633148","observation_id":"e3789745-18de-4722-a992-3c5f61bd9346","resolution":{"observed_at":"2026-08-07T05:44:53.121625Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.125326Z","title":"Exploring the potential of large language models (llms) in learning on graphs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.125326Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:b2c621ed8bf49384e7e5618c768dd550321488969656f72f510f99061ab07cd5","observation_id":"b24d5736-3731-47af-9483-9d28057fd1f5","resolution":{"observed_at":"2026-08-07T05:44:53.125326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04668","last_updated":"2024-02-24T06:44:45Z","snapshot_observed_at":"2026-08-16T14:54:18.914340Z","submitted_at":"2023-10-07T03:14:11Z","title":"Label-free Node Classification on Graphs with Large Language Models (LLMS)","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04668","snapshot_observed_at":"2026-08-07T05:44:53.128259Z","title":"Label-free node classification on graphs with large language models (llms)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.128259Z"},"links":{"cited_paper":"/paper/2310.04668","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:d00ec7967aa301c3603b13a9bc820c0637f2f17aa440a169f3522ed03b9ffb66","observation_id":"f2d1ab24-7e01-409b-b891-c099e4b72148","resolution":{"observed_at":"2026-08-07T05:44:53.128259Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.00064","last_updated":"2022-03-11T14:02:28Z","snapshot_observed_at":"2026-08-16T17:45:19.760306Z","submitted_at":"2021-10-29T19:55:12Z","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.00064","snapshot_observed_at":"2026-08-07T05:44:53.131783Z","title":"Node feature extraction by self-supervised multi-scale neighborhood prediction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.131783Z"},"links":{"cited_paper":"/paper/2111.00064","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:bf4467dfa3f3ce829bb7a3bd268d098d1c8638e1ade71930aa6f09ed344f86e8","observation_id":"8ae971d1-94b8-4585-aa81-8a213aab78f8","resolution":{"observed_at":"2026-08-07T05:44:53.131783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.135198Z","title":"Less is more: Attention supervision with counterfactuals for text classification","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.135198Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:80f343b680d893cfd90e14b18196fb87d70e84b32fa73ef2f0aee05bde5e7301","observation_id":"b1cb2fea-6fab-43a0-9c46-a0fae393bc5c","resolution":{"observed_at":"2026-08-07T05:44:53.135198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.138112Z","title":"Human attention in visual question answering: Do humans and deep networks look at the same regions? Computer Vision and Image Understanding, 163:90–100, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.138112Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:4632dca73fcc928feca62d93832790e307be2b379d79c93d23325c0f1beb9719","observation_id":"7b7eb758-0ca2-44ec-93d7-eab93686c123","resolution":{"observed_at":"2026-08-07T05:44:53.138112Z","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":"2026-08-14T18:16:28.847993Z","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":"2026-08-07T05:44:53.141033Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.141033Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:7cf30f648701823f307589e13fadb701444cbdf6744a5a7755e7b12059a39fcd","observation_id":"dff9a44d-10b0-46dc-a0dd-d80880088b20","resolution":{"observed_at":"2026-08-07T05:44:53.141033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.02565","last_updated":"2023-08-03T07:00:04Z","snapshot_observed_at":"2026-08-16T15:11:09.026714Z","submitted_at":"2023-08-03T07:00:04Z","title":"SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.02565","snapshot_observed_at":"2026-08-07T05:44:53.143927Z","title":"Simteg: A frustratingly simple approach improves textual graph learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.143927Z"},"links":{"cited_paper":"/paper/2308.02565","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:918d8b5fc806f8d562d393da625c892f0a81266f7e41c4f9f711db068409d491","observation_id":"a12c2620-6c17-4bba-a01b-18da132bdb4c","resolution":{"observed_at":"2026-08-07T05:44:53.143927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.147109Z","title":"Going beyond xai: A systematic survey for explanation-guided learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.147109Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:2ca85bd6862a7cc94a410ec6f894898ccd8916a6e5fe6b3df2d3bcf03e5b5aeb","observation_id":"5ee96681-b61b-4a05-b87f-897aafc643b2","resolution":{"observed_at":"2026-08-07T05:44:53.147109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.150057Z","title":"Gnes: Learning to explain graph neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.150057Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:01bb1e7afad5a525be4d25ca6c7e9fbdd79bb9bb3dd2432331641800f2299777","observation_id":"420d61f4-dd3c-439e-8283-230b388f81fc","resolution":{"observed_at":"2026-08-07T05:44:53.150057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.152911Z","title":"Res: A robust framework for guiding visual explanation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.152911Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:d1f2b92f55ae84b1b0470daac43c3901b3c9b8b87dcf8b31c8bdea10bf098cb5","observation_id":"b86a26d8-4b1b-41ab-8f20-9151a0d05d58","resolution":{"observed_at":"2026-08-07T05:44:53.152911Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08649","last_updated":"2019-04-04T04:42:28Z","snapshot_observed_at":"2026-08-14T17:12:31.754765Z","submitted_at":"2019-02-22T19:38:36Z","title":"Saliency Learning: Teaching the Model Where to Pay Attention","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08649","snapshot_observed_at":"2026-08-07T05:44:53.156055Z","title":"Saliency learning: Teaching the model where to pay attention","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.156055Z"},"links":{"cited_paper":"/paper/1902.08649","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:c6afdae5735c8c3116f084f41d348658ecd45c603843719a8bee8f5446d67b13","observation_id":"f8af793b-9825-424e-85a2-3c7ffab67152","resolution":{"observed_at":"2026-08-07T05:44:53.156055Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.159424Z","title":"Citeseer: An automatic citation indexing system","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.159424Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:13024e88e23483098f7a977b8b4d6e5081416725f94e68b9e6df9d03801b9128","observation_id":"039a2acc-5700-4ba0-931c-9d1fc48e9272","resolution":{"observed_at":"2026-08-07T05:44:53.159424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.162458Z","title":"Lee Giles, Kurt D","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.162458Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:f41cf609c00f20e384938b02a4e3f578ff9f6b5bf6cf7d3e09090b15cd4843b0","observation_id":"3f554ab2-f63e-4e88-879c-728322716293","resolution":{"observed_at":"2026-08-07T05:44:53.162458Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.165300Z","title":"A fundamental model with stable interpretability for traffic forecasting","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.165300Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:960675488fb729eb420e8d8691669e879b16e20eaf29d1f2310dd15c59ac25d6","observation_id":"44dea314-4e2c-4fbb-8431-3f91df2774c5","resolution":{"observed_at":"2026-08-07T05:44:53.165300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.168342Z","title":"node2vec: Scalable feature learning for networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.168342Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:244501df988f27d8c76a63aca1e92d0307a6a478e6c7710ee352370253892774","observation_id":"f452da46-c789-4fd8-bf8e-30384ad85d64","resolution":{"observed_at":"2026-08-07T05:44:53.168342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.171310Z","title":"Inductive representation learning on large graphs","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.171310Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:49b87b759be77c8e038face30df3b48cfa4ae5f0b7f45264760d7a4e2786e4e7","observation_id":"64758c76-77e6-4319-99af-e1dc9982ab07","resolution":{"observed_at":"2026-08-07T05:44:53.171310Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19523","last_updated":"2024-03-07T02:45:36Z","snapshot_observed_at":"2026-08-16T15:28:05.962866Z","submitted_at":"2023-05-31T03:18:03Z","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19523","snapshot_observed_at":"2026-08-07T05:44:53.174216Z","title":"Harnessing explanations: Llm-to-lm interpreter for enhanced text-attributed graph representation learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.174216Z"},"links":{"cited_paper":"/paper/2305.19523","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:b0d4616cb625fd23476d5d51a74fc0c869189b4940ae08bbeb6eb7435a675754","observation_id":"921d6402-cfc2-420c-a420-0311fc9aa56f","resolution":{"observed_at":"2026-08-07T05:44:53.174216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.177478Z","title":"Multitask asynchronous metalearning for few-shot anomalous node detection in dynamic networks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.177478Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:5dfccda8bf05ae370b37fe0c5c6278b550b0111419a09ba90e7567f059c24a9b","observation_id":"52920c44-1ceb-41ee-b195-15bdea84e3ba","resolution":{"observed_at":"2026-08-07T05:44:53.177478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18992","last_updated":"2025-03-19T20:33:22Z","snapshot_observed_at":"2026-08-16T13:39:09.952170Z","submitted_at":"2024-06-27T08:33:35Z","title":"Semi-supervised Concept Bottleneck Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.18992","snapshot_observed_at":"2026-08-07T05:44:53.180247Z","title":"Semi-supervised concept bottleneck models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.180247Z"},"links":{"cited_paper":"/paper/2406.18992","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:85c067d25b21da4ef6e300ec39a009eec95a2a2be0b85474f4007940952b41af","observation_id":"36cd7a0e-adc4-422c-9628-7fdb0ac1cfe1","resolution":{"observed_at":"2026-08-07T05:44:53.180247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.06950","last_updated":"2024-10-09T14:47:12Z","snapshot_observed_at":"2026-08-16T13:11:04.889228Z","submitted_at":"2024-10-09T14:47:12Z","title":"Faithful Interpretation for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2410.06950","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.06950","snapshot_observed_at":"2026-08-07T05:44:53.630259Z","title":"Faithful Interpretation for Graph Neural Networks","venue":"cs.LG","work_id":"f2a56d6a-ebe7-4394-8507-be10279810fd","year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.183727Z"},"links":{"cited_paper":"/paper/2410.06950","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:90fe7e47527dfa3c3e0fa35133cce5b3f675f6bc6350bf7faed216ca71370060","observation_id":"38c883f8-f601-4e22-a446-6c25caea66c9","resolution":{"observed_at":"2026-08-07T05:44:53.633721Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.186917Z","title":"Towards multi-dimensional explanation alignment for medical classification","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.186917Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:1e483238f8757dedcbec2fa6817c7c2051fcb95271a0eed6ae36e48a2e75f59e","observation_id":"0069d8e0-0f25-423b-982b-f38d4c71270a","resolution":{"observed_at":"2026-08-07T05:44:53.186917Z","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":"2026-08-07T05:44:54.091699Z","title":"Seat: stable and explainable attention","venue":null,"work_id":"6a15830e-1129-4dd6-97a8-82b276bc42b0","year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.189701Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:a811815bd3fd2cf369158c336f14ec33eefb218e892c4dda80b1ac5d4d72c825","observation_id":"e6e6386e-01ac-476d-a037-6cf307775389","resolution":{"observed_at":"2026-08-07T05:44:54.095283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:54.081583Z","title":"Improving interpretation faithfulness for vision transformers","venue":null,"work_id":"acaf2aea-ddd5-44c2-8052-1c510c216935","year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.192693Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:852bc14fec0c2fa54c76f2864de5815ce9d0fc0eb532f5d6898ddbfa1249ee41","observation_id":"024a6bdd-0c99-4aca-b0a3-da656400bbf7","resolution":{"observed_at":"2026-08-07T05:44:54.085594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15476","last_updated":"2025-02-01T12:03:52Z","snapshot_observed_at":"2026-08-16T13:49:47.284992Z","submitted_at":"2024-05-24T11:55:46Z","title":"Editable Concept Bottleneck Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15476","snapshot_observed_at":"2026-08-07T05:44:53.195529Z","title":"Editable concept bottleneck models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.195529Z"},"links":{"cited_paper":"/paper/2405.15476","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:bf72f8a0aaee84abd6b11702ebc86fb3506a264b5f400fc6d8e25dbcef6aeb4e","observation_id":"8992f4e9-feed-4d54-8ff2-d6728a2dbbad","resolution":{"observed_at":"2026-08-07T05:44:53.195529Z","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":"2026-08-07T05:44:54.071111Z","title":"Towards stable and explainable attention mechanisms","venue":null,"work_id":"3bc1dfdb-a2c3-4b57-9318-f1f69592f640","year":2025},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.198693Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:9435c960d1c9707d2ff3c9607361ea0ef3f120f159dfee44a90a01b07b1d25d6","observation_id":"61aeae77-79a1-4454-adc3-c175f6b848c1","resolution":{"observed_at":"2026-08-07T05:44:54.075479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.201620Z","title":"Open graph benchmark: Datasets for machine learning on graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.201620Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:67c771375f144ccc46d6814c8da2d7341c98b1fb610d405eb951d41bd8898e67","observation_id":"4fb6c46f-5828-488a-9540-c3ec1f59c34c","resolution":{"observed_at":"2026-08-07T05:44:53.201620Z","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":"2026-08-07T05:44:54.057005Z","title":"Gpt-gnn: Generative pre-training of graph neural networks","venue":null,"work_id":"b0b4d483-9f09-4a8e-855c-989dd8814a9a","year":2020},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.204568Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:aa0d80c28b94d0a2fd319b3d93a9374fb7c73506748e7200e9bda2d12950afd3","observation_id":"ad01c1ad-243a-4f3a-9419-1e9c52ce48d0","resolution":{"observed_at":"2026-08-07T05:44:54.060216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00115","last_updated":"2020-04-30T21:45:40Z","snapshot_observed_at":"2026-07-06T09:16:43.105433Z","submitted_at":"2020-04-30T21:45:40Z","title":"Learning to Faithfully Rationalize by Construction","version":1},"cited_work":{"arxiv_id":"2005.00115","doi":null,"metadata_source":"pith","pith_arxiv_id":"2005.00115","snapshot_observed_at":"2026-08-07T05:44:53.610088Z","title":"Learning to Faithfully Rationalize by Construction","venue":"cs.CL","work_id":"89f957ed-ca9e-4414-bf31-d12bc177f68e","year":2020},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.207642Z"},"links":{"cited_paper":"/paper/2005.00115","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:e347e55ba156a7efa352bc7ee5703e5d89e24e2bd8d9e65e4829e24901b8a4c8","observation_id":"40ed85b4-3f0e-4eed-bbd1-7dfcbfecb299","resolution":{"observed_at":"2026-08-07T05:44:53.613370Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12976","last_updated":"2023-05-22T12:32:06Z","snapshot_observed_at":"2026-08-16T15:31:07.022633Z","submitted_at":"2023-05-22T12:32:06Z","title":"Attentive Graph-based Text-aware Preference Modeling for Top-N Recommendation","version":1},"cited_work":{"arxiv_id":"2305.12976","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.12976","snapshot_observed_at":"2026-08-07T05:44:53.597479Z","title":"Attentive Graph-based Text-aware Preference Modeling for Top-N Recommendation","venue":"cs.IR","work_id":"fc3bcee8-991e-49f9-9a8a-7cba3a2ab355","year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.210725Z"},"links":{"cited_paper":"/paper/2305.12976","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:ed1a10611fe44cbae63fbd1929443f59a33ba965bdc352e28958d2aacf4c55c4","observation_id":"788cdf8c-7d16-429b-8f46-9d83010f4b8d","resolution":{"observed_at":"2026-08-07T05:44:53.600956Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.213897Z","title":"A new status index derived from sociometric analysis","venue":null,"work_id":null,"year":1953},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.213897Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:b9832f9f56cb3fc0212f86e353ae4ff349c14bb45e40ea60582b20ebed93e5cd","observation_id":"704bf263-7a30-4d26-968f-56bbe01d9317","resolution":{"observed_at":"2026-08-07T05:44:53.213897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-13T11:38:10.906031Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-07T05:44:53.217337Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.217337Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:ebcbfff2239894157441b5e5787dc38838cdb6e5c90aa6b8618769ff4fd901b8","observation_id":"16a98564-7b59-4091-8105-afdcd52170ff","resolution":{"observed_at":"2026-08-07T05:44:53.217337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07308","last_updated":"2016-11-21T11:37:17Z","snapshot_observed_at":"2026-08-14T21:29:27.927932Z","submitted_at":"2016-11-21T11:37:17Z","title":"Variational Graph Auto-Encoders","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.07308","snapshot_observed_at":"2026-08-07T05:44:53.220550Z","title":"Variational graph auto-encoders","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.220550Z"},"links":{"cited_paper":"/paper/1611.07308","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:469431e99790c2722ed1f9412401cf2351aea6608f0c4442826867d625915abd","observation_id":"b1824393-ad7e-4201-bd58-eb90a72530f6","resolution":{"observed_at":"2026-08-07T05:44:53.220550Z","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":"2026-08-07T05:44:54.042407Z","title":"Faithful vision- language interpretation via concept bottleneck models","venue":null,"work_id":"f74463cc-b509-4fab-af15-838745bad72c","year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.223567Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:62c8ffcab2e8f1c7a63ce3e6cc4664b32916f5125310744e8ab4205a57a8e524","observation_id":"b62433b4-9251-4e68-ba83-c3cf5626a2a2","resolution":{"observed_at":"2026-08-07T05:44:54.045857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:54.032269Z","title":"Training graph neural networks with 1000 layers","venue":null,"work_id":"a58de956-12eb-42f8-8f8b-d9b93413acd6","year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.226449Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:66b56b6477f17c92785271c5232a6a0e82793c304ab700d1c804858ef02c6062","observation_id":"fb112402-558d-4c54-957d-5b92e3e661e5","resolution":{"observed_at":"2026-08-07T05:44:54.036231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:54.021510Z","title":"Evaluating graph neural networks for link prediction: Current pitfalls and new benchmarking","venue":null,"work_id":"a6e6484d-b733-4ba2-83d0-607b1fa4d033","year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.229486Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:c2708b49dce0f9365d201815dfa00d951ea2a94811d623812cb873b6e34a9e8a","observation_id":"28573a53-a00c-42bd-9713-5ee247c8e1e7","resolution":{"observed_at":"2026-08-07T05:44:54.025397Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:54.011322Z","title":"The link prediction problem for social net- works","venue":null,"work_id":"6e92107e-5391-408e-bbe4-0fb64fc4e321","year":2003},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.232828Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:a270fa5b7d9e4a424188e755d06b763fc0637de35376148ce4abf303d4045e13","observation_id":"b533cdee-ce1c-47bd-9122-73cf4a892a5c","resolution":{"observed_at":"2026-08-07T05:44:54.015387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.08819","last_updated":"2019-06-11T14:14:34Z","snapshot_observed_at":"2026-08-14T19:12:19.791103Z","submitted_at":"2018-05-22T19:12:47Z","title":"Learning what and where to attend","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.08819","snapshot_observed_at":"2026-08-07T05:44:53.236379Z","title":"Learning what and where to attend","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.236379Z"},"links":{"cited_paper":"/paper/1805.08819","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:8f6302bbc4a3f9f1feb26d07ea47839777e22ef9c1fe671043f28aa4b068f7ef","observation_id":"2a932a56-d6de-4b83-acc3-4d0de008a72d","resolution":{"observed_at":"2026-08-07T05:44:53.236379Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.239489Z","title":"Taad: Time-varying adversarial anomaly detection in dynamic graphs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.239489Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:970261cf8d0afe438631efed6c88987df3c8fe2fe099c75f6957e150bc9e0372","observation_id":"a1598fb2-2425-4d04-a0b7-915aa9f3c671","resolution":{"observed_at":"2026-08-07T05:44:53.239489Z","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":"2026-08-16T14:56:22.157264Z","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":"2026-08-07T05:44:53.242558Z","title":"One for all: Towards training one graph model for all classification tasks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.242558Z"},"links":{"cited_paper":"/paper/2310.00149","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:e4e4a026687f5ae2110cfccc81bc3b801842fcdf80b0e2ab6d60be44d0b7d231","observation_id":"dd0c25b5-6daa-44e1-87ea-7fba408ee48a","resolution":{"observed_at":"2026-08-07T05:44:53.242558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00793","last_updated":"2024-11-07T20:01:16Z","snapshot_observed_at":"2026-08-16T14:56:03.808279Z","submitted_at":"2023-10-01T21:09:59Z","title":"Revisiting Link Prediction: A Data Perspective","version":3},"cited_work":{"arxiv_id":"2310.00793","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.00793","snapshot_observed_at":"2026-08-07T05:44:53.551118Z","title":"Revisiting Link Prediction: A Data Perspective","venue":"cs.SI","work_id":"2f66a231-3592-4f36-8705-afb7ca8f5dd0","year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.245695Z"},"links":{"cited_paper":"/paper/2310.00793","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:aea23cfcc7064ff009b4c0fc216c7c4680653e05d8c7b7be56a6d5316f2dfaa5","observation_id":"be1f0745-0dbb-43d3-8f43-d2b02ce79358","resolution":{"observed_at":"2026-08-07T05:44:53.556298Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.249178Z","title":"Automating the construction of internet portals with machine learning","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.249178Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:f74eb73f4fa70486370ffb83bf3ed0cf53fd47a9aea4a1f6e3f01036f4dfb711","observation_id":"2b26f8a2-5403-4ca8-850e-7bf6e8390b08","resolution":{"observed_at":"2026-08-07T05:44:53.249178Z","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":"2026-08-07T05:44:53.991693Z","title":"Link prediction via matrix factorization","venue":null,"work_id":"3046b6f1-f5b2-4fb8-b1a6-5d0a90c55ef2","year":2011},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.252185Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:aa868b34cf1a884bb393cec3e9fb4631c78f12abed91220f1a62c01da443cc32","observation_id":"e2629a44-0594-421b-a88e-63a01cca11df","resolution":{"observed_at":"2026-08-07T05:44:53.995043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.03540","last_updated":"2019-12-19T06:16:51Z","snapshot_observed_at":"2026-08-14T16:34:59.154101Z","submitted_at":"2019-05-09T11:32:44Z","title":"Embedding Human Knowledge into Deep Neural Network via Attention Map","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.03540","snapshot_observed_at":"2026-08-07T05:44:53.255081Z","title":"Embedding human knowledge into deep neural network via attention map","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.255081Z"},"links":{"cited_paper":"/paper/1905.03540","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:909fc42ba63af6ac457e4a980d9d4762730d9f4aa65a328296ec6798a4a1ddc2","observation_id":"a4142f2b-a5d5-4281-91b0-901039772563","resolution":{"observed_at":"2026-08-07T05:44:53.255081Z","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":"2026-08-07T05:44:53.982447Z","title":"Clustering and preferential attachment in growing networks.Physical review E, 64(2):025102, 2001","venue":null,"work_id":"09d393a5-9fcb-485c-bd07-dffece211d21","year":2001},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.258559Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:60d13a02dbdad2e80698d47e0c890be4de768d3aa9c4bcd1d57303d5d7a23ca5","observation_id":"8b475d33-7e71-49b5-a737-dadcb1157a81","resolution":{"observed_at":"2026-08-07T05:44:53.985853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12022","last_updated":"2024-08-06T03:34:06Z","snapshot_observed_at":"2026-08-16T14:17:23.510194Z","submitted_at":"2024-02-19T10:31:53Z","title":"Distilling Large Language Models for Text-Attributed Graph Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12022","snapshot_observed_at":"2026-08-07T05:44:53.261714Z","title":"Distilling large language models for text-attributed graph learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.261714Z"},"links":{"cited_paper":"/paper/2402.12022","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:9289598e50fef295a4933f040c9a2913fe286d96d491c5c2407cfd42bc32869d","observation_id":"f02112c5-87b0-4e26-a16f-af05cf9a1589","resolution":{"observed_at":"2026-08-07T05:44:53.261714Z","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":"2026-08-07T05:44:53.973308Z","title":"Exploring human-like attention supervision in visual question answering","venue":null,"work_id":"0cbe92df-b9e5-4bdf-b618-e192c8442c0b","year":2018},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.264786Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:67e0f2ac9c0d7a63ea38c0592e70e44805ab6e9d0090b860c223ace02257c8ba","observation_id":"ce6e982b-bd4d-4fa1-a89d-e820c5b4e41d","resolution":{"observed_at":"2026-08-07T05:44:53.976841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.18152","last_updated":"2024-03-09T16:08:16Z","snapshot_observed_at":"2026-08-16T14:48:16.178231Z","submitted_at":"2023-10-27T14:00:04Z","title":"Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.18152","snapshot_observed_at":"2026-08-07T05:44:53.267780Z","title":"Disentangled representation learning with large language models for text-attributed graphs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.267780Z"},"links":{"cited_paper":"/paper/2310.18152","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:6b498f81056798c8b41b535e9c82e4fa65829c1412853c869a91545dba6aeae7","observation_id":"baa968b0-8722-4e9e-89e2-93fd971213a3","resolution":{"observed_at":"2026-08-07T05:44:53.267780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.03717","last_updated":"2017-05-25T05:38:45Z","snapshot_observed_at":"2026-08-14T21:12:28.443292Z","submitted_at":"2017-03-10T15:35:32Z","title":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.03717","snapshot_observed_at":"2026-08-07T05:44:53.270916Z","title":"Right for the right rea- sons: Training differentiable models by constraining their explanations","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.270916Z"},"links":{"cited_paper":"/paper/1703.03717","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:ad52355173477e9d460b7b1d5102aa0d803621921a7c93741ab8b75ac81a8d22","observation_id":"61cee1d1-b488-466c-9afd-9b7643970d64","resolution":{"observed_at":"2026-08-07T05:44:53.270916Z","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":"2026-08-07T05:44:53.963995Z","title":"Saliency guided experience packing for replay in continual learning","venue":null,"work_id":"1db2d54e-ba21-4ebc-a223-91ec39bedb21","year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.274129Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:ffd4dafe443cf22e783585312636840f093f4a6d87f1f182d7064a7eda690d85","observation_id":"2820bed8-cc61-4fc5-9697-57da203a1b06","resolution":{"observed_at":"2026-08-07T05:44:53.967560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.276996Z","title":"Collective classification in network data","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.276996Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:bcd6b2ba45cbaf7cb4033b9d6110bdc8858f3612e77424b9bb900db62e95555a","observation_id":"8140ef89-55d8-43e2-8cab-9340ea9e9dec","resolution":{"observed_at":"2026-08-07T05:44:53.276996Z","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":"2026-08-07T05:44:53.949567Z","title":"Supervising model attention with human explanations for robust natural language inference","venue":null,"work_id":"110be383-5df1-4246-8a0a-0d5a3ed36fa2","year":2022},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.279974Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:bb75dede1a698bf5b321e2de72174f2e04ef92097081eee94cad25ad4c1bdc3e","observation_id":"dbc706a5-84d0-4228-8f77-fae0583afb72","resolution":{"observed_at":"2026-08-07T05:44:53.952874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.13714","last_updated":"2019-05-31T16:49:57Z","snapshot_observed_at":"2026-08-14T16:22:54.824580Z","submitted_at":"2019-05-31T16:49:57Z","title":"Do Human Rationales Improve Machine Explanations?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.13714","snapshot_observed_at":"2026-08-07T05:44:53.283428Z","title":"Do human rationales improve machine explanations? arXiv preprint arXiv:1905.13714, 2019","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.283428Z"},"links":{"cited_paper":"/paper/1905.13714","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:3b6efd7f3a5466dd0632720648094302205dd2b5271bddf335e0211f80d73a6c","observation_id":"6112f007-52cb-4558-b759-a9c2806e13ed","resolution":{"observed_at":"2026-08-07T05:44:53.283428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.09376","last_updated":"2021-07-01T10:08:16Z","snapshot_observed_at":"2026-08-16T18:30:31.512980Z","submitted_at":"2021-04-19T15:08:06Z","title":"Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.09376","snapshot_observed_at":"2026-08-07T05:44:53.286572Z","title":"Scalable and adaptive graph neural networks with self-label-enhanced training","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.286572Z"},"links":{"cited_paper":"/paper/2104.09376","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:fe2ad3eb2993347beace2435184f3800a459cdf1c3a3b0e162ccc8b9e33eef81","observation_id":"81041e00-b878-47f0-a37b-78cc893d86fc","resolution":{"observed_at":"2026-08-07T05:44:53.286572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.14324","last_updated":"2025-02-23T03:40:49Z","snapshot_observed_at":"2026-08-16T14:40:44.616353Z","submitted_at":"2023-11-24T07:53:48Z","title":"Large Language Models as Topological Structure Enhancers for Text-Attributed Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.14324","snapshot_observed_at":"2026-08-07T05:44:53.289692Z","title":"Large language models as topological structure enhancers for text-attributed graphs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.289692Z"},"links":{"cited_paper":"/paper/2311.14324","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:3db77a0ca8b7701b3118feef2010f5121013287b4cbef3dbe38fb83028b86b6d","observation_id":"da52ecd8-802e-44c1-8c78-46be6e213b6c","resolution":{"observed_at":"2026-08-07T05:44:53.289692Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-07T05:44:53.292846Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.292846Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:1f152af3858403f3ca42b4578d477f9b5720fabd48453a8b164fdaf7de0011f0","observation_id":"9f272e06-f256-46c3-a9c1-2ce9e2c89ad4","resolution":{"observed_at":"2026-08-07T05:44:53.292846Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.295890Z","title":"Neural discrete representation learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.295890Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:824fa13926582bdb718ba114e7d9d026eaf0e0ed64774faedcd41cd9976d3497","observation_id":"24a9c9fd-660e-48e7-baf1-98cf839be13e","resolution":{"observed_at":"2026-08-07T05:44:53.295890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.298858Z","title":"Graph attention networks, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.298858Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:ef7620cd7fbbda2ea6a7b86deccfcd9302e9600410f966d1bc2e527619136583","observation_id":"ee14c13e-709e-4003-bb52-60958be9150e","resolution":{"observed_at":"2026-08-07T05:44:53.298858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.301836Z","title":"Inductive graph unlearning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.301836Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:cc9d00168fce49566017bf848829bf9f1167594272da2e1b8925c9decafb8539","observation_id":"e0505033-1d5f-420d-a08e-c1063ae2a37f","resolution":{"observed_at":"2026-08-07T05:44:53.301836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.00199","last_updated":"2022-06-22T21:37:18Z","snapshot_observed_at":"2026-08-16T17:17:56.169434Z","submitted_at":"2022-03-01T03:08:47Z","title":"Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.00199","snapshot_observed_at":"2026-08-07T05:44:53.304734Z","title":"Equivariant and stable positional encoding for more powerful graph neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.304734Z"},"links":{"cited_paper":"/paper/2203.00199","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:e21f292e6141c9bad32110c2c8d793f94168cc07874c2c4150f4fe8364a9ffb0","observation_id":"14ff625c-9baa-44dd-834a-cbd31407ffa8","resolution":{"observed_at":"2026-08-07T05:44:53.304734Z","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":"2026-08-07T05:44:53.924812Z","title":"Epm: Evolutionary perception method for anomaly detection in noisy dynamic graphs","venue":null,"work_id":"9f95cdd4-97b5-4c23-8a7c-e690a74ff534","year":2025},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.307973Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:d0589cf3f038d7c81f87686adbdf01c634bff811d1695a4a1445914250322816","observation_id":"2741b64d-bce8-47fa-bb13-152b36ce78bc","resolution":{"observed_at":"2026-08-07T05:44:53.928319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.915827Z","title":"Persistent local homology in graph learning","venue":null,"work_id":"d07d48e7-d494-4e1a-91c3-e74f5fb870e0","year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.310906Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:c1556f9ee75a50f0a58702c0097ee7e8b17e5307d0461337a35985cba9f379a0","observation_id":"abeb366c-31b6-43b4-a4e9-bb4a0c0bd28c","resolution":{"observed_at":"2026-08-07T05:44:53.918997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.313841Z","title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.313841Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:859caa6701b74df99904d41fd8a80dc88f08b26e9b9fa2b7365241905aceba33","observation_id":"41868234-bf34-4f05-8cf6-8d6bc016786e","resolution":{"observed_at":"2026-08-07T05:44:53.313841Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.00890","last_updated":"2024-06-04T05:46:09Z","snapshot_observed_at":"2026-08-16T15:58:19.383596Z","submitted_at":"2023-02-02T05:45:09Z","title":"Neural Common Neighbor with Completion for Link Prediction","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.00890","snapshot_observed_at":"2026-08-07T05:44:53.316924Z","title":"Neural common neighbor with completion for link prediction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.316924Z"},"links":{"cited_paper":"/paper/2302.00890","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:0d670e6ff5c3981e63ae78e09a363f36a44a60c64d297132a252a0ee8f44919e","observation_id":"c92a220b-a027-43b1-bdb5-9aa6c180eb00","resolution":{"observed_at":"2026-08-07T05:44:53.316924Z","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":"2026-08-07T05:44:53.900148Z","title":"Preserving node-level privacy in graph neural networks","venue":null,"work_id":"f26b9ed9-5aeb-4201-a1fc-82439585ba42","year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.320070Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:e3a3e70fe606224ae74836264b67edbedc0c4736a3f52362399a0de8d4516cf6","observation_id":"48373330-6d9e-4876-ad3a-40cf1582dfaa","resolution":{"observed_at":"2026-08-07T05:44:53.904224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.890156Z","title":"A comprehensive study on text-attributed graphs: Benchmarking and rethinking","venue":null,"work_id":"52c38dd5-eaa1-4ca9-8659-1b43ead603ab","year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.323085Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:1d88437dc19878f31298079001d7ef681c9758f44814e184e5a66f92ad879e68","observation_id":"76321aaf-b40e-4573-ae25-baadc14704fe","resolution":{"observed_at":"2026-08-07T05:44:53.894323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.879747Z","title":"Network rep- resentation learning with rich text information","venue":null,"work_id":"7a35540a-4851-4fc6-b784-e3867fd17c80","year":2015},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.326076Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:c1610e08bad0f31bcaa38a6a969d5aabbfa76bd930a644c6e927731cf22aaa24","observation_id":"3c32e4f2-b6e6-409a-bd2b-2fc75a23090e","resolution":{"observed_at":"2026-08-07T05:44:53.884300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.870192Z","title":"Graphformers: Gnn-nested transformers for representation learning on textual graph","venue":null,"work_id":"5a70e069-801e-4162-88d5-ebda3288e8f1","year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.328993Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:967b43641f564c9df6a9c4bf8af53cf85a1359ca72b5d53b672a742886138e00","observation_id":"9861f3ba-1ad2-41d9-b377-421c61ebc964","resolution":{"observed_at":"2026-08-07T05:44:53.873948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.861148Z","title":"Deep bidirectional language-knowledge graph pretraining","venue":null,"work_id":"7307d9d4-e934-43bc-8957-7517664f64ad","year":2022},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.332266Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:23eb98ef97b76f11ea635b42bc0057d62a1a7f0d9a0aa53041bfbc2a801d3fc5","observation_id":"bb5f516c-71db-40e5-a547-5cb1b75c9ae7","resolution":{"observed_at":"2026-08-07T05:44:53.864417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.07134","last_updated":"2024-02-06T03:08:44Z","snapshot_observed_at":"2026-08-16T15:08:39.189907Z","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":"2026-08-07T05:44:53.335317Z","title":"Natural language is all a graph needs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.335317Z"},"links":{"cited_paper":"/paper/2308.07134","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:5acb579d9bdf78f6669b455ad3090d2114a1d3a1140fbff5388ebdc1318f17ba","observation_id":"8ff1dd83-ce1d-4bc4-9e3c-7db73604027b","resolution":{"observed_at":"2026-08-07T05:44:53.335317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.338508Z","title":"Do transformers really perform badly for graph representation? Advances in neural information processing systems, 34:28877–28888, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.338508Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:9d18900ea4af7c0a46a805edccbe1dc55a7850925ef076ed38dbf2596fbc5221","observation_id":"2f9e59fc-54b7-48f8-9be8-de1caa168714","resolution":{"observed_at":"2026-08-07T05:44:53.338508Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.09872","last_updated":"2024-12-10T16:06:29Z","snapshot_observed_at":"2026-08-16T14:52:00.449235Z","submitted_at":"2023-10-15T16:04:28Z","title":"Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.09872","snapshot_observed_at":"2026-08-07T05:44:53.341577Z","title":"Empower text-attributed graphs learning with large language models (llms)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.341577Z"},"links":{"cited_paper":"/paper/2310.09872","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:aa9498e1c9cfa2cd61f6c1edca9194ac455e51e8c6403dbf51c52f4dd75835d0","observation_id":"1c2cca25-2e2f-49f4-970c-059e0bd4bc7a","resolution":{"observed_at":"2026-08-07T05:44:53.341577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:44:53.344779Z","title":"Neo-gnns: Neighborhood overlap-aware graph neural networks for link prediction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.344779Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:32dd6e8e0feb27b59f6f458ec1f5f852fd409028abcf8073147f75d93718c55c","observation_id":"3c9e0f11-4432-426a-abc6-7acc187c3a96","resolution":{"observed_at":"2026-08-07T05:44:53.344779Z","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":"2026-08-07T05:44:53.841743Z","title":"Fast multi-resolution trans- former fine-tuning for extreme multi-label text classification","venue":null,"work_id":"71e3ee68-3f28-4af3-ba4d-b276b5c0af57","year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.347761Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:b962284e42a3e53ecb034130ef6c6a917de3b3b8f0bfab2d53616c9959d434e4","observation_id":"953dfbda-e1c5-4ad5-9ce6-58bc9c0e5f43","resolution":{"observed_at":"2026-08-07T05:44:53.845026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.350678Z","title":"Labeling trick: A theory of using graph neural networks for multi-node representation learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.350678Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:79605b960352577675676996d4f14f7b9b8ba031bf558341c3b80d009a80735b","observation_id":"18cbc971-b689-4a87-8927-09f564663308","resolution":{"observed_at":"2026-08-07T05:44:53.350678Z","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":"2026-08-07T05:44:53.826215Z","title":"A multi- classification division-aggregation framework for fake news detection","venue":null,"work_id":"50884c11-6ada-410a-978c-4d411421adbd","year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.353528Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:7f68d70ab50e6439a9cea98d38d824e97761a6b98502d6f72d466f51ca10cb0c","observation_id":"e6fab6f6-7532-47b6-aacd-6b12d27231c5","resolution":{"observed_at":"2026-08-07T05:44:53.830280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.816817Z","title":"Magi: Multi-annotated explanation-guided learning","venue":null,"work_id":"873b5cf6-3efb-4b89-84f7-ed5d0fc14c95","year":1977},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.356625Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:50227e035a1fde5aca5cf1ff327b882613ac4e7a383d675a384f5435d9c1ab8f","observation_id":"e01aa1bf-8277-46a4-97e6-e28e82481974","resolution":{"observed_at":"2026-08-07T05:44:53.820239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.806492Z","title":"Interpretable visual question answering by visual grounding from attention supervision mining","venue":null,"work_id":"78ef9ec8-bad3-4b28-8799-9c3e2721ad23","year":2019},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.359407Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:4a3dbb85b443a52ee561c55c7dda828dc1c019ccedd119e1b46559473ed33863","observation_id":"6de096b3-2187-420f-b066-12be7a763002","resolution":{"observed_at":"2026-08-07T05:44:53.810251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.14709","last_updated":"2023-03-01T14:09:04Z","snapshot_observed_at":"2026-08-16T16:20:58.318407Z","submitted_at":"2022-10-26T13:40:57Z","title":"Learning on Large-scale Text-attributed Graphs via Variational Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.14709","snapshot_observed_at":"2026-08-07T05:44:53.362133Z","title":"Learning on large-scale text-attributed graphs via variational inference","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.362133Z"},"links":{"cited_paper":"/paper/2210.14709","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:1c04fb2cbf3bcbb52edd0a70ce61266184e964c5fd204b41bc4b809dd466017d","observation_id":"c87b8347-df82-49df-a030-c4aca0b043df","resolution":{"observed_at":"2026-08-07T05:44:53.362133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.06870","last_updated":"2019-08-19T15:11:27Z","snapshot_observed_at":"2026-08-16T21:16:51.614491Z","submitted_at":"2019-08-19T15:11:27Z","title":"Fine-grained Sentiment Analysis with Faithful Attention","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.06870","snapshot_observed_at":"2026-08-07T05:44:53.365271Z","title":"Fine-grained sentiment analysis with faithful attention","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.365271Z"},"links":{"cited_paper":"/paper/1908.06870","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:cb759a9048e57d80c97c0dcd5e79da95bef3ff2ccbc07e161df5f5f7d969643d","observation_id":"0e627d09-bc7e-41da-a878-22da89d26016","resolution":{"observed_at":"2026-08-07T05:44:53.365271Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.01843","last_updated":"2019-07-22T08:25:16Z","snapshot_observed_at":"2026-08-14T16:03:51.678874Z","submitted_at":"2019-07-22T08:25:16Z","title":"GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.01843","snapshot_observed_at":"2026-08-07T05:44:53.368460Z","title":"Gear: Graph-based evidence aggregating and reasoning for fact verification","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.368460Z"},"links":{"cited_paper":"/paper/1908.01843","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:4bf8b493f0c189b888177381e5623c2ddda7372d05ed8272dcef2c6c5c1b62d4","observation_id":"35431791-a9c7-49eb-ad77-6006a08c54d0","resolution":{"observed_at":"2026-08-07T05:44:53.368460Z","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":"2026-08-07T05:44:53.796424Z","title":"Predicting missing links via local information","venue":null,"work_id":"708e6b1f-3ced-423b-9b03-bd1854010921","year":2009},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.371519Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:f098d374304951e5764db3912a9f3cf3d8e36ead669f2242049dc65706e1fb03","observation_id":"6072726d-9199-45ee-85a6-a6b2c3fecc2e","resolution":{"observed_at":"2026-08-07T05:44:53.800302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.786581Z","title":"Textgnn: Improving text encoder via graph neural network in sponsored search","venue":null,"work_id":"a82ff49d-0b79-4ea8-aae5-7fe6fde8a81f","year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.374466Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:1246f1244e9ce9688474156f3d00bff104c6c5a41b693b77b260b5407d598190","observation_id":"3272582b-9810-48cc-bdc1-b11dc0e2bef5","resolution":{"observed_at":"2026-08-07T05:44:53.790431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.15569","last_updated":"2024-07-24T08:56:11Z","snapshot_observed_at":"2026-08-16T14:23:57.053271Z","submitted_at":"2024-01-28T05:12:09Z","title":"Efficient Tuning and Inference for Large Language Models on Textual Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.15569","snapshot_observed_at":"2026-08-07T05:44:53.377716Z","title":"Efficient tuning and inference for large language models on textual graphs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.377716Z"},"links":{"cited_paper":"/paper/2401.15569","citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:57f36785bece32f779f999627851c70dc2583e79cd12bb018b8426c4e74d4171","observation_id":"7cc3575c-96c3-4198-8cdc-769b4bca6e7e","resolution":{"observed_at":"2026-08-07T05:44:53.377716Z","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":"2026-08-07T05:44:53.773305Z","title":"Neural bellman-ford networks: A general graph neural network framework for link prediction","venue":null,"work_id":"c1421c9a-f14d-4cba-a7cc-e8b233ac87e9","year":2021},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.380942Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:dfdd1aeca44d364f6fb0cb5f33f337c6caa8088b2803c321004db184fbb18d4f","observation_id":"14e8eb68-3854-4ecf-9689-e60719d059a1","resolution":{"observed_at":"2026-08-07T05:44:53.780507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.763593Z","title":null,"venue":null,"work_id":"0f814dbe-f43e-498a-ab3c-b1a15d35075d","year":2023},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.384236Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:071c39850d6d133dd110e9d913cf0155e3f576f75310557f8d62c033a6187b31","observation_id":"d9b224dd-677e-48a3-9df3-2f652e39c38f","resolution":{"observed_at":"2026-08-07T05:44:53.766533Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.754470Z","title":null,"venue":null,"work_id":"c0dc7b5d-7fb8-414c-9cbb-d5ea384e3fa4","year":null},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.387569Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:4ca7d69f0d80897eabe7cf2709be7e1e8a33deb8192a2f9e317c95923d9edf16","observation_id":"b1fcf67d-2a16-4e27-b0c8-8cc106ff33e0","resolution":{"observed_at":"2026-08-07T05:44:53.757592Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.745514Z","title":null,"venue":null,"work_id":"b70e1f34-0095-4cfa-a12d-a366b2fcde5e","year":null},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.390740Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:9fd98c8ad432cd7f6e3d8b2acffb4337f6dd9d43eab03f3d5934f799c999c26a","observation_id":"a075c833-aa94-4a4f-b628-a7c8778c49f4","resolution":{"observed_at":"2026-08-07T05:44:53.748623Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.736414Z","title":null,"venue":null,"work_id":"a71d903d-76de-4c5b-a6ab-636384ae1949","year":null},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.393814Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:581175de40a1ed858975981262f80d277c7e04601fdb7b144cf197728d6aec27","observation_id":"a75800a9-4f03-41fc-b301-2b6c793d0324","resolution":{"observed_at":"2026-08-07T05:44:53.739626Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T05:44:53.727004Z","title":"And you should tell me what knowledge is needed to understand the concepts","venue":null,"work_id":"82efa699-3ee5-419e-8814-cfadcc64491e","year":null},"citing_paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-07T05:44:53.396903Z"},"links":{"citing_paper":"/paper/2506.07168"},"observation_digest":"sha256:5eebc8dc0ffb026eb6a6280e275ccd04d7788ad35575dc86a80731ac83d40bc6","observation_id":"002f7c7d-cceb-4d59-9849-043a2655f734","resolution":{"observed_at":"2026-08-07T05:44:53.730356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.07168","last_updated":"2025-06-08T14:34:29Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T13:22:20.290679Z","submitted_at":"2025-06-08T14:34:29Z","title":"Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment"},"reference_resolution":{"displayed":95,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":63,"verified_exact":4,"verified_fuzzy":28},"total_outbound_references":95},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 95 of 95 outbound references and 0 inbound Pith citation observations for arXiv:2506.07168."}