{"as_of":"2026-08-10T11:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3dfb69e4555e184a9dc974c96cea9c84bdd7c3de5dae13fe69a31ffa905b3fb4","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:37:11.894861Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.10539/citation-record","integrity":"/paper/2507.10539/integrity","json":"/paper/2507.10539/citation-record.json","paper":"/paper/2507.10539"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.15204","last_updated":"2025-01-03T11:44:51Z","snapshot_observed_at":"2026-08-04T21:07:04.238345Z","submitted_at":"2024-12-19T18:59:17Z","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15204","snapshot_observed_at":"2026-08-06T17:37:11.615199Z","title":"Long- bench v2: Towards deeper understanding and reason- ing on realistic long-context multitasks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.615199Z"},"links":{"cited_paper":"/paper/2412.15204","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:de4ce0b99c0cb175cb3457823ff4262e3a2a07b333343b9914d77bb5a4af619e","observation_id":"24546205-eb5b-4fe1-ad01-9bf27bf0d3ea","resolution":{"observed_at":"2026-08-06T17:37:11.615199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.07666","last_updated":"2023-03-14T07:15:41Z","snapshot_observed_at":"2026-07-06T15:03:00.555225Z","submitted_at":"2023-03-14T07:15:41Z","title":"Relational Multi-Task Learning: Modeling Relations between Data and Tasks","version":1},"cited_work":{"arxiv_id":"2303.07666","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.07666","snapshot_observed_at":"2026-08-06T17:37:13.061913Z","title":"Relational Multi-Task Learning: Modeling Relations between Data and Tasks","venue":"cs.LG","work_id":"43d3c3d1-6fd5-4001-aad2-1dcd21e5100a","year":2023},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.635991Z"},"links":{"cited_paper":"/paper/2303.07666","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:83b1671cc44ca3526b519f456fd694850416908462b336ccb72b6cd92ba38a4f","observation_id":"688f52a7-f3f2-490a-869c-66fb6d915311","resolution":{"observed_at":"2026-08-06T17:37:13.069665Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10997","last_updated":"2024-03-27T09:16:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-18T07:47:33Z","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10997","snapshot_observed_at":"2026-08-06T17:37:11.668297Z","title":"Retrieval-augmented generation for large language models: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.668297Z"},"links":{"cited_paper":"/paper/2312.10997","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:e9305c7a8935f1251b263218b01cda9b99a12a0f0466adb7d066670a92cde7f7","observation_id":"97fb6b5a-3d9b-49de-8d73-f466e4e75735","resolution":{"observed_at":"2026-08-06T17:37:11.668297Z","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":"2026-08-06T17:37:13.381347Z","title":"In Multi-Modal-Paper, there are 58565 text-nodes, 7380 figure-nodes, and 6792 table-nodes","venue":null,"work_id":"0c45551c-8726-4089-b6b5-e18a93937142","year":2022},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.852810Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:101fe2d755b21617c36f3c47b51cdad38d90cacfabcda612535907f76ec619d3","observation_id":"908ddbe7-7d19-47fa-a0f4-d52e28d4167c","resolution":{"observed_at":"2026-08-06T17:37:13.390706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:37:13.342787Z","title":"It includes three datasets of different scales, with the sizes ranging from small to large as follows: Baby, Sports, and Clothing","venue":null,"work_id":"d0c29408-bdbd-4faa-8a89-d6a7add659fd","year":2015},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.858565Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:69e9279f339c7ba7f28dc9d7ffbd636cea5c42ca4982bffee361b61c93203812","observation_id":"1706e829-811c-43e3-9139-0747ea931f8b","resolution":{"observed_at":"2026-08-06T17:37:13.359877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-07-06T05:10:16.862707Z","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":"2026-08-06T17:37:11.695006Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.695006Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:d3e59cc1c9d891470f544df722f378ba4b1681f9bcc23c878d6a4a5a9307d26d","observation_id":"c3877b74-ee8c-46f4-9983-55cb273be5cd","resolution":{"observed_at":"2026-08-06T17:37:11.695006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-07-06T10:29:18.734092Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-06T17:37:11.700718Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.700718Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:9dd720cf2aea51862fd915c1e3f087ebd0da7e0aef2af0f154e0a3ea144eb89a","observation_id":"62b6e055-9e33-47bf-8034-19ae286ab472","resolution":{"observed_at":"2026-08-06T17:37:11.700718Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.07452","last_updated":"2023-02-15T03:53:26Z","snapshot_observed_at":"2026-08-05T15:37:43.888534Z","submitted_at":"2023-02-15T03:53:26Z","title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.07452","snapshot_observed_at":"2026-08-06T17:37:11.706811Z","title":"How to train your dragon: Di- verse augmentation towards generalizable dense retrieval","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.706811Z"},"links":{"cited_paper":"/paper/2302.07452","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:479a26e18bd8b9eb0c2283b1df82221fe482d372964a66efbb79690eecac495b","observation_id":"94aea020-4ed2-4a53-9dfa-c5c2a9b8e749","resolution":{"observed_at":"2026-08-06T17:37:11.706811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00149","last_updated":"2024-07-12T23:01:32Z","snapshot_observed_at":"2026-07-06T16:25:46.699214Z","submitted_at":"2023-09-29T21:15:26Z","title":"One for All: Towards Training One Graph Model for All Classification Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00149","snapshot_observed_at":"2026-08-06T17:37:11.713264Z","title":"One for all: Towards training one graph model for all classification tasks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.713264Z"},"links":{"cited_paper":"/paper/2310.00149","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:1435073b4137e9ee8d81b73e78ee7903910f0d8102b9639a90982caed2bd5aff","observation_id":"c0db666d-0e3c-4450-8925-73551a9f76d9","resolution":{"observed_at":"2026-08-06T17:37:11.713264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02170","last_updated":"2024-11-15T04:30:04Z","snapshot_observed_at":"2026-08-07T04:49:42.215176Z","submitted_at":"2023-10-03T16:05:48Z","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02170","snapshot_observed_at":"2026-08-06T17:37:11.721122Z","title":"Dy- namic llm-agent network: An llm-agent collaboration framework with agent team optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.721122Z"},"links":{"cited_paper":"/paper/2310.02170","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:f141882a2a6601a47d1d5d807489d4ef8bd7f42441bed8572a5a567576b6f7c5","observation_id":"245fa440-bd69-4ca9-942c-0ae28d6ac339","resolution":{"observed_at":"2026-08-06T17:37:11.721122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.13311","last_updated":"2022-07-22T06:04:06Z","snapshot_observed_at":"2026-08-09T12:00:53.393601Z","submitted_at":"2022-01-25T12:44:23Z","title":"Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer","version":2},"cited_work":{"arxiv_id":"2201.13311","doi":null,"metadata_source":"pith","pith_arxiv_id":"2201.13311","snapshot_observed_at":"2026-08-06T17:37:12.629192Z","title":"Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer","venue":"cs.IR","work_id":"53a72a2f-82ac-4c6d-98ac-b66faf8f5abe","year":2022},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.726126Z"},"links":{"cited_paper":"/paper/2201.13311","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:3d9d05cca46d074f28e04b54522d58b066b1485d261f6f21853336d0d542efdb","observation_id":"2c1e1f53-9e5d-4ef0-8ddc-ee3369e35cf5","resolution":{"observed_at":"2026-08-06T17:37:12.637315Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15379","last_updated":"2023-09-27T03:15:52Z","snapshot_observed_at":"2026-07-06T16:24:10.053246Z","submitted_at":"2023-09-27T03:15:52Z","title":"A Content-Driven Micro-Video Recommendation Dataset at Scale","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15379","snapshot_observed_at":"2026-08-06T17:37:11.733457Z","title":"A content-driven micro-video recommen- dation dataset at scale","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.733457Z"},"links":{"cited_paper":"/paper/2309.15379","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:2a67eda5f9ff402e83fc05567ba38a1d3cc064c1936eb374210623e34ee3a369","observation_id":"68dd66cb-7e76-4ba2-b229-5d5980026926","resolution":{"observed_at":"2026-08-06T17:37:11.733457Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-09T18:02:17.307812Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-06T17:37:11.739439Z","title":"Dinov2: Learning robust visual features without supervision","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.739439Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:683ac77dd77885fdf3ac86f763872ab154880544c4d71d92217d8399f33d42c4","observation_id":"035e07f8-7313-4126-ac27-9b6e6c286fbb","resolution":{"observed_at":"2026-08-06T17:37:11.739439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03277","last_updated":"2023-04-06T17:58:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-06T17:58:09Z","title":"Instruction Tuning with GPT-4","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.03277","snapshot_observed_at":"2026-08-06T17:37:11.746775Z","title":"Instruc- tion tuning with gpt-4","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.746775Z"},"links":{"cited_paper":"/paper/2304.03277","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:c3ac127b2945fa940bed401d2bd23073e3fd5c20941ae88e9ba54cd304006b85","observation_id":"aba5e883-504e-4c5f-83cd-1cc0dc987ea8","resolution":{"observed_at":"2026-08-06T17:37:11.746775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.08921","last_updated":"2024-09-10T15:38:56Z","snapshot_observed_at":"2026-08-10T10:50:20.156541Z","submitted_at":"2024-08-15T12:20:24Z","title":"Graph Retrieval-Augmented Generation: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.08921","snapshot_observed_at":"2026-08-06T17:37:11.753365Z","title":"Graph retrieval-augmented generation: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.753365Z"},"links":{"cited_paper":"/paper/2408.08921","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:d2e9980298e2dd5172b03cd81d70357c8fe388ffc320349be2ebd9745b053890","observation_id":"24c5bbd3-d9d1-4334-81c4-d2232be765ac","resolution":{"observed_at":"2026-08-06T17:37:11.753365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.06103","last_updated":"2017-10-26T19:53:49Z","snapshot_observed_at":"2026-07-06T05:34:10.015525Z","submitted_at":"2017-03-17T17:09:14Z","title":"Modeling Relational Data with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.06103","snapshot_observed_at":"2026-08-06T17:37:11.759330Z","title":"Modeling relational data with graph convolutional networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.759330Z"},"links":{"cited_paper":"/paper/1703.06103","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:81f7d4cbb4f932899752000463ad0c86e304fc1db463626272ea9fb914efa39a","observation_id":"be861abd-2bdd-478b-9ce8-9ba80f13e0c5","resolution":{"observed_at":"2026-08-06T17:37:11.759330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03768","last_updated":"2021-03-14T22:44:38Z","snapshot_observed_at":"2026-08-08T17:40:47.037804Z","submitted_at":"2020-10-08T05:13:36Z","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03768","snapshot_observed_at":"2026-08-06T17:37:11.772925Z","title":"Alfworld: Aligning text and embodied environments for interactive learning","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.772925Z"},"links":{"cited_paper":"/paper/2010.03768","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:ed9cf1b2719d016cc69a84cd48fc26a836e832184e357d2466dc7bb87a461bdd","observation_id":"0d5ba0fb-9e2e-4b32-bcfb-28265ff57f78","resolution":{"observed_at":"2026-08-06T17:37:11.772925Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.14655","last_updated":"2022-11-26T20:13:22Z","snapshot_observed_at":"2026-08-09T22:14:49.256277Z","submitted_at":"2022-11-26T20:13:22Z","title":"How Crucial is Transformer in Decision Transformer?","version":1},"cited_work":{"arxiv_id":"2211.14655","doi":null,"metadata_source":"pith","pith_arxiv_id":"2211.14655","snapshot_observed_at":"2026-08-06T17:37:12.377139Z","title":"How Crucial is Transformer in Decision Transformer?","venue":"cs.LG","work_id":"6fc72c5d-6d0d-4f6d-8611-65e15f32ecf8","year":2022},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.778727Z"},"links":{"cited_paper":"/paper/2211.14655","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:225813d2166c7d7a6ca260512d244bfe40ebe7bffac577a2d7d99d34ec7c92fb","observation_id":"cca24aec-ec33-4e8f-b612-ca4cd3f9131e","resolution":{"observed_at":"2026-08-06T17:37:12.386360Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-06T17:37:11.790648Z","title":"Graph attention networks.arXiv preprint arXiv:1710.10903, 2017a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.790648Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:b5608f7a782c550e1ad7e0d4a3bee82cf776a54b2de9acc9331380c2cae9bcd9","observation_id":"992037fc-684e-4b1f-b4bd-0b3a160ba00e","resolution":{"observed_at":"2026-08-06T17:37:11.790648Z","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":"2026-08-06T17:37:11.795814Z","title":"doi: 10.18653/v1/P19-1248","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.795814Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:9161f5481d249a3a4a9384cc2b8420980b2018ac90619b0cfd63d44493f775c4","observation_id":"494922af-184b-4d15-831f-03addbff4a93","resolution":{"observed_at":"2026-08-06T17:37:11.795814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15223","last_updated":"2024-10-31T08:58:08Z","snapshot_observed_at":"2026-08-07T05:55:25.949233Z","submitted_at":"2024-05-24T05:29:12Z","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15223","snapshot_observed_at":"2026-08-06T17:37:11.802704Z","title":"ivideogpt: Interactive videogpts are scalable world models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.802704Z"},"links":{"cited_paper":"/paper/2405.15223","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:52053703a51a8a41eedf62431a9acf9bc4981c2c5cc4545cb560e140e658d9c8","observation_id":"b2a5669e-4915-4dd4-bec9-05687ca1924a","resolution":{"observed_at":"2026-08-06T17:37:11.802704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11483","last_updated":"2024-07-24T20:53:10Z","snapshot_observed_at":"2026-07-06T18:01:40.563108Z","submitted_at":"2024-04-17T15:40:45Z","title":"AgentKit: Structured LLM Reasoning with Dynamic Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11483","snapshot_observed_at":"2026-08-06T17:37:11.809555Z","title":"Y ., Prabhumoye, S., McAleer, S., Bisk, Y ., Salakhutdinov, R., Li, Y ., and Mitchell, T","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.809555Z"},"links":{"cited_paper":"/paper/2404.11483","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:5029297d779c63f759d0264f38b32306cdff193ccd2450e991e52cec821c5443","observation_id":"526d851c-7684-4dc9-b798-26d76c1142b9","resolution":{"observed_at":"2026-08-06T17:37:11.809555Z","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":"2026-08-06T17:37:11.815838Z","title":"Adding conditional control to text-to-image diffusion models","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.815838Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:815a319cbe2e18b3ea5f30eb08eea2308b623d2fbcc9ecba2b6f195cafb75bcf","observation_id":"3139b2dd-fb0a-43e0-9152-323169400ad8","resolution":{"observed_at":"2026-08-06T17:37:11.815838Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.19473","last_updated":"2024-06-21T08:26:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-02-29T18:59:01Z","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.19473","snapshot_observed_at":"2026-08-06T17:37:11.822232Z","title":"Retrieval-augmented generation for ai-generated content: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.822232Z"},"links":{"cited_paper":"/paper/2402.19473","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:80e27cf46d683d4bf0557219e77be504922c152ec9f1887ac33fc03134c38c95","observation_id":"90942ef8-c7ac-44ef-abf8-2284473b892c","resolution":{"observed_at":"2026-08-06T17:37:11.822232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04384","last_updated":"2023-05-02T14:15:02Z","snapshot_observed_at":"2026-08-09T11:19:32.271760Z","submitted_at":"2022-06-09T09:51:42Z","title":"Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2206.04384","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.04384","snapshot_observed_at":"2026-08-06T17:37:12.022970Z","title":"Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning","venue":"cs.LG","work_id":"c71970ab-fa04-4014-a5c1-a8150eae2e2e","year":2022},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.828554Z"},"links":{"cited_paper":"/paper/2206.04384","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:666d174d7f6c5423edc6f1659b7255147112576043bb9484657d9d63f14b9c0b","observation_id":"a1e1728a-81ed-41d9-8b96-6455f44da34f","resolution":{"observed_at":"2026-08-06T17:37:12.036492Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16823","last_updated":"2024-08-22T13:06:51Z","snapshot_observed_at":"2026-08-01T23:06:25.314616Z","submitted_at":"2024-02-26T18:48:27Z","title":"Language Agents as Optimizable Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16823","snapshot_observed_at":"2026-08-06T17:37:11.837113Z","title":"Language agents as optimizable graphs","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.837113Z"},"links":{"cited_paper":"/paper/2402.16823","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:11526712f077bc38e31bf2bd8a24231ddbe681efa57ecb617f0303c87c38d659","observation_id":"cce25671-f081-433d-a384-3e46d69ddd93","resolution":{"observed_at":"2026-08-06T17:37:11.837113Z","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":"2026-08-06T17:37:13.410483Z","title":null,"venue":null,"work_id":"1628b307-2e58-49a7-a394-503d7739bf20","year":2024},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.846291Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:2d23e48dfff63e08e24f63fe3220f9cb58182bcf7bad3bdef750d36749564e8e","observation_id":"cec6b718-b6c9-4e4d-9164-209892be5473","resolution":{"observed_at":"2026-08-06T17:37:13.418204Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:37:13.298572Z","title":"Molecular struc- tures and graph representations are generated from SMILES strings, with atoms (nodes) and bonds (edges) described using natural language","venue":null,"work_id":"72ece301-7518-4d00-b0b7-9d74b21c86dc","year":2017},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.865567Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:2aef3ee925232990218412d8615b68259516a4ae52412e587b01e82b289ca813","observation_id":"2006e9f1-414f-4281-ae16-8c5d2e88b4d5","resolution":{"observed_at":"2026-08-06T17:37:13.310024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:37:13.271002Z","title":null,"venue":null,"work_id":"35736f79-a7ca-4de8-b856-c0669392e19a","year":2020},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.871809Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:8aa326c06961fa9fa4fbb5eabf984ddd48d27985247ca643a6b053123ccc5d3f","observation_id":"816f3f3b-5b88-4457-a774-be572b991cec","resolution":{"observed_at":"2026-08-06T17:37:13.282682Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:37:13.197765Z","title":"Here we finetune it on the dataset of this task","venue":null,"work_id":"6220692e-8f69-4308-8274-137e2a39af3c","year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.887951Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:b572d05787ca4cd0316a577346b2ae029a893583884aeaf53b8d334928d7ac85","observation_id":"631cb9be-f5e2-4abc-a49d-7f19e08ddf3b","resolution":{"observed_at":"2026-08-06T17:37:13.214723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:37:13.163159Z","title":"This task is to generate a response that integrates information from the retrieved documents to accurately address the user’s query","venue":null,"work_id":"d40093ec-041c-4fdd-b4a8-371147a31e65","year":1990},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.894861Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:cf0a22e7c339c14625c4a838d0d1c83fdd4c66b7e5a4b6d779cfa906abd75d07","observation_id":"3dd07953-8d63-47f1-9c3b-552427510452","resolution":{"observed_at":"2026-08-06T17:37:13.178377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:37:13.243590Z","title":"Their details are as follows: • BM25: A widely-used ranking function in information sparse retrieval","venue":null,"work_id":"4e946464-113d-468d-9eed-7f1dc7a74a78","year":2023},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.880336Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:c14a82daf2ebf16f3b79c212d562a35117b988705fc0ca8113946a0477a78bea","observation_id":"31091688-b765-4438-8ca9-566af9075a94","resolution":{"observed_at":"2026-08-06T17:37:13.250737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16130","last_updated":"2025-02-19T10:49:41Z","snapshot_observed_at":"2026-07-06T18:05:11.700127Z","submitted_at":"2024-04-24T18:38:11Z","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16130","snapshot_observed_at":"2026-08-06T17:37:11.656712Z","title":"From local to global: A graph rag approach to query-focused summarization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.656712Z"},"links":{"cited_paper":"/paper/2404.16130","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:97e9199389b28f31d4089d13c9011a4484aa85778bba0ec6a6762f1236e04153","observation_id":"6f6ee02b-8e36-406f-85cf-045064d774f8","resolution":{"observed_at":"2026-08-06T17:37:11.656712Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.09202","last_updated":"2020-02-11T13:46:23Z","snapshot_observed_at":"2026-08-10T01:54:38.540449Z","submitted_at":"2018-10-22T12:17:40Z","title":"Graph Convolutional Reinforcement Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.09202","snapshot_observed_at":"2026-08-06T17:37:11.682878Z","title":"Graph convolutional reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.682878Z"},"links":{"cited_paper":"/paper/1810.09202","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:40384a52a5d5a961963710129fea8503b45a0576f3941ea29e6c152eb633c7ca","observation_id":"77e5204f-182a-4342-b8a1-b0c335c8ae20","resolution":{"observed_at":"2026-08-06T17:37:11.682878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-06T17:37:11.676498Z","title":"J., Shen, Y ., Wallis, P., Allen-Zhu, Z., Li, Y ., Wang, S., Wang, L., and Chen, W","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.676498Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:f2e77ca641b14892749b77be1983a39a6569c94a1856f86cab23dbb46f617dc4","observation_id":"60c5dc34-e1fd-4164-ac2d-5df5c4a96c18","resolution":{"observed_at":"2026-08-06T17:37:11.676498Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07960","last_updated":"2025-05-25T02:19:37Z","snapshot_observed_at":"2026-07-30T08:34:47.046912Z","submitted_at":"2024-05-13T17:38:53Z","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07960","snapshot_observed_at":"2026-08-06T17:37:11.767207Z","title":"Agentclinic: a multimodal agent bench- mark to evaluate ai in simulated clinical environments","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.767207Z"},"links":{"cited_paper":"/paper/2405.07960","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:7574bcaad240dc31c2a580053108dd87d891a7876359c7b6b2eaa705d57c4efa","observation_id":"a49c74e6-ca89-413d-9f01-cd29ea155041","resolution":{"observed_at":"2026-08-06T17:37:11.767207Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.07157","last_updated":"2024-10-09T17:56:15Z","snapshot_observed_at":"2026-07-06T19:30:34.984716Z","submitted_at":"2024-10-09T17:56:15Z","title":"InstructG2I: Synthesizing Images from Multimodal Attributed Graphs","version":1},"cited_work":{"arxiv_id":"2410.07157","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.07157","snapshot_observed_at":"2026-08-06T17:37:12.808976Z","title":"InstructG2I: Synthesizing Images from Multimodal Attributed Graphs","venue":"cs.AI","work_id":"2d52654b-5309-4490-a097-7802245a18fa","year":2024},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.689682Z"},"links":{"cited_paper":"/paper/2410.07157","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:8a02ba1d4ca92325f1c61790577024350b89234baffee853c448e0f619bc1fa8","observation_id":"422dcf4e-4c0b-4814-a78b-aaed8b9cf168","resolution":{"observed_at":"2026-08-06T17:37:12.817774Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:37:13.432913Z","title":"M., Hao, Y ., Stoeckius, M., Smibert, P., and Satija, R","venue":null,"work_id":"87549054-dbc8-43b4-9dea-b778d80d4e2d","year":1902},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.785580Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:46b2a559a4ab8ffdf55d690dbc77cafa0f985f3b3eaf189d2c90a3b7d7d3ea77","observation_id":"9f63e06b-3963-4cda-b6a2-56c9ca6d6bf2","resolution":{"observed_at":"2026-08-06T17:37:13.442519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-06T17:37:11.630570Z","title":"Bruce, J., Dennis, M","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.630570Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:c2e166080527ec0769324f4dc83aa54651ce09673a2f76dda262aa0197d4c393","observation_id":"0dd94efa-5324-4623-91ab-57dfdad3a3f4","resolution":{"observed_at":"2026-08-06T17:37:11.630570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08170","last_updated":"2024-04-11T05:01:12Z","snapshot_observed_at":"2026-08-04T08:10:16.676870Z","submitted_at":"2024-02-13T02:03:26Z","title":"LLaGA: Large Language and Graph Assistant","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.08170","snapshot_observed_at":"2026-08-06T17:37:11.642954Z","title":"Llaga: Large language and graph assistant","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.642954Z"},"links":{"cited_paper":"/paper/2402.08170","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:d208d6d7c6440f3b2e21107e90b66302ec9721babb1b142894225442303d8dc2","observation_id":"a202db81-c566-4a5d-9310-2d5d1dc4a940","resolution":{"observed_at":"2026-08-06T17:37:11.642954Z","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":"2026-08-06T17:37:13.463256Z","title":"Exploring the po- tential of large language models (llms) in learning on graphs","venue":null,"work_id":"11d5cdb5-41ff-4867-a442-b392f4826147","year":2023},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.649811Z"},"links":{"citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:ae75cb0b691f6965ca30d4dc5a701319d3a6dfd8df7aa4389c2febeb5dc14b08","observation_id":"f5f60979-9887-4db8-9cc5-c0ec06732100","resolution":{"observed_at":"2026-08-06T17:37:13.469858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.04615","last_updated":"2023-12-07T18:51:41Z","snapshot_observed_at":"2026-07-06T16:58:32.099526Z","submitted_at":"2023-12-07T18:51:41Z","title":"Relational Deep Learning: Graph Representation Learning on Relational Databases","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.04615","snapshot_observed_at":"2026-08-06T17:37:11.662125Z","title":"E., Ranjan, R., Robinson, J., Ying, R., You, J., and Leskovec, J","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.662125Z"},"links":{"cited_paper":"/paper/2312.04615","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:99a0273cde71ced197fa0677dd75ff470f8a4d3b95d497e36853a5c2c55cbd60","observation_id":"66143597-0f3b-4c5d-b2a8-aa708f4801c3","resolution":{"observed_at":"2026-08-06T17:37:11.662125Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.05150","last_updated":"2020-12-02T17:52:35Z","snapshot_observed_at":"2026-07-31T17:17:17.205582Z","submitted_at":"2020-04-10T17:54:09Z","title":"Longformer: The Long-Document Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.05150","snapshot_observed_at":"2026-08-06T17:37:11.621975Z","title":"E., and Cohan, A","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:11.621975Z"},"links":{"cited_paper":"/paper/2004.05150","citing_paper":"/paper/2507.10539"},"observation_digest":"sha256:06ae5ec835e6ffc12d6af2905c3abae28dfe9f3fc55881709f444f02b60c532f","observation_id":"0aab8ac4-9d2b-4e76-bd58-ff83b0be4d64","resolution":{"observed_at":"2026-08-06T17:37:11.621975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.10539","last_updated":"2025-07-14T17:57:45Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T14:14:07.441053Z","submitted_at":"2025-07-14T17:57:45Z","title":"Graph World Model"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":30,"verified_exact":4,"verified_fuzzy":8},"total_outbound_references":43},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2507.10539."}