{"as_of":"2026-08-08T18:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7fa5d31b09f1d94167919b90b4207c2d5715536caf920551d5c0157e63d33084","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:13:02.136813Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2506.00261/citation-record","integrity":"/paper/2506.00261/integrity","json":"/paper/2506.00261/citation-record.json","paper":"/paper/2506.00261"},"outbound":[{"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":"2026-08-07T12:12:59.824845Z","title":"arXiv preprint arXiv:2312.10997, 2:1","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:59.824845Z"},"links":{"cited_paper":"/paper/2312.10997","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:1867eca6f15a71d5a53805eccc5fe52ffdcd2c51a45d46338535446ff114e7eb","observation_id":"97926a7d-49b0-4cbe-8565-79bf8f7fb20d","resolution":{"observed_at":"2026-08-07T12:12:59.824845Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16506","last_updated":"2025-07-12T11:09:06Z","snapshot_observed_at":"2026-07-06T18:20:05.707144Z","submitted_at":"2024-05-26T10:11:40Z","title":"GRAG: Graph Retrieval-Augmented Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.16506","snapshot_observed_at":"2026-08-07T12:13:00.097322Z","title":"arXiv preprint arXiv:2405.16506","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:00.097322Z"},"links":{"cited_paper":"/paper/2405.16506","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:d1a3d9d25637e4ec19bcfe15abda8f74cee8336cbd764699510f062103801a95","observation_id":"70aa4c1f-0dc6-4973-aec9-f01f7fcbf45e","resolution":{"observed_at":"2026-08-07T12:13:00.097322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.20724","last_updated":"2025-02-05T17:45:24Z","snapshot_observed_at":"2026-07-06T19:40:34.668379Z","submitted_at":"2024-10-28T04:39:32Z","title":"Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.20724","snapshot_observed_at":"2026-08-07T12:13:00.201806Z","title":"arXiv preprint arXiv:2410.20724","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:00.201806Z"},"links":{"cited_paper":"/paper/2410.20724","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:ae6071471e7a493c38ae094c6d03fb5a0d826119267bb64fbe4293ee970f5ca0","observation_id":"53a39ea2-516a-40b8-b208-2c7e76d9b9ac","resolution":{"observed_at":"2026-08-07T12:13:00.201806Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18742","last_updated":"2023-05-30T04:46:28Z","snapshot_observed_at":"2026-08-06T06:41:07.331068Z","submitted_at":"2023-05-30T04:46:28Z","title":"Graph Reasoning for Question Answering with Triplet Retrieval","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18742","snapshot_observed_at":"2026-08-07T12:13:00.332779Z","title":"arXiv preprint arXiv:2305.18742","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:00.332779Z"},"links":{"cited_paper":"/paper/2305.18742","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:f9ba76bf27c065066fdc798f1f8442835459599b13b09700be89fc8a52d1b90a","observation_id":"3610ce65-58c9-4da4-959c-59d39e4e3fc8","resolution":{"observed_at":"2026-08-07T12:13:00.332779Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01061","last_updated":"2024-02-24T03:03:12Z","snapshot_observed_at":"2026-07-06T16:26:26.426279Z","submitted_at":"2023-10-02T10:14:43Z","title":"Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01061","snapshot_observed_at":"2026-08-07T12:13:00.673773Z","title":"arXiv preprint arXiv:2310.01061","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:00.673773Z"},"links":{"cited_paper":"/paper/2310.01061","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:caf7eae0582f98772fce9de57ac6b53c2ff2c2782b5d78c545f6557789ec71f8","observation_id":"fa7c700b-5e6f-4100-861d-25e37f480757","resolution":{"observed_at":"2026-08-07T12:13:00.673773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.20139","last_updated":"2024-05-30T15:14:24Z","snapshot_observed_at":"2026-08-08T05:24:30.960406Z","submitted_at":"2024-05-30T15:14:24Z","title":"GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20139","snapshot_observed_at":"2026-08-07T12:13:00.775082Z","title":"arXiv preprint arXiv:2405.20139","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:00.775082Z"},"links":{"cited_paper":"/paper/2405.20139","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:fb8bf9346a33932f5e1b3f0afa3cc53112a57f9b90d6f5ab44484298542a3593","observation_id":"367c1c31-137b-4f5f-a3b2-1e57e96c502a","resolution":{"observed_at":"2026-08-07T12:13:00.775082Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.03868","last_updated":"2020-04-13T16:25:54Z","snapshot_observed_at":"2026-07-06T08:35:53.531562Z","submitted_at":"2019-11-10T06:58:44Z","title":"Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.03868","snapshot_observed_at":"2026-08-07T12:13:00.885821Z","title":"arXiv preprint arXiv:1911.03868","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:00.885821Z"},"links":{"cited_paper":"/paper/1911.03868","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:be56e7c0c10f3b9dcb614c6a8e1f8e865ffbf31c5f27fb4c659efbce33d44f24","observation_id":"d3f471da-c0b6-4d0e-ad85-747509f79519","resolution":{"observed_at":"2026-08-07T12:13:00.885821Z","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":"2026-07-06T19:01:41.274385Z","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":"2026-08-07T12:13:01.207797Z","title":"arXiv preprint arXiv:2408.08921","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:01.207797Z"},"links":{"cited_paper":"/paper/2408.08921","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:f704e35ddd14e3e5d3b03b92cb415e8dd0a5a9201c7a55fc696dae1c7e484432","observation_id":"6b076808-df74-43ec-b6c7-251ba70d1935","resolution":{"observed_at":"2026-08-07T12:13:01.207797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-08-07T12:13:01.293822Z","title":"ArXiv, abs/1910.01108","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:01.293822Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:9786761dbf69706f2cb2b7df1caa1ee3a5421074c7ff61c7b5bf491acb6b85b2","observation_id":"bcaccb7b-d96c-481c-9a02-f1942402a951","resolution":{"observed_at":"2026-08-07T12:13:01.293822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.06643","last_updated":"2018-03-18T11:28:12Z","snapshot_observed_at":"2026-07-06T06:28:52.591595Z","submitted_at":"2018-03-18T11:28:12Z","title":"The Web as a Knowledge-base for Answering Complex Questions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.06643","snapshot_observed_at":"2026-08-07T12:13:01.392760Z","title":"arXiv preprint arXiv:1803.06643","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:01.392760Z"},"links":{"cited_paper":"/paper/1803.06643","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:f71f6fd646b975667ce47fa5014ecf657e3482d0df0a2a571296ba1163768da1","observation_id":"95fd2b68-7112-45bc-9b0a-4d69127c540e","resolution":{"observed_at":"2026-08-07T12:13:01.392760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.01313","last_updated":"2024-01-08T16:19:17Z","snapshot_observed_at":"2026-07-06T17:10:56.398607Z","submitted_at":"2024-01-02T17:56:30Z","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.01313","snapshot_observed_at":"2026-08-07T12:13:01.544584Z","title":"arXiv preprint arXiv:2401.01313,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:01.544584Z"},"links":{"cited_paper":"/paper/2401.01313","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:672a60a5d7a4b9dd45f58b25112248719e189e843712b0162d77f1aa6239386e","observation_id":"cdc9dfcd-8861-48db-a5ee-441e5310f6ed","resolution":{"observed_at":"2026-08-07T12:13:01.544584Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-07T12:13:01.672305Z","title":"arXiv preprint arXiv:2307.09288","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:01.672305Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:4fcb2332feb563646345c53cf3b1997cb969928f9396105980b7c9e160462733","observation_id":"eaafe864-4e83-4f28-b7a7-52b9db216fd7","resolution":{"observed_at":"2026-08-07T12:13:01.672305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01219","last_updated":"2025-09-14T09:34:46Z","snapshot_observed_at":"2026-07-06T16:13:46.112815Z","submitted_at":"2023-09-03T16:56:48Z","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.01219","snapshot_observed_at":"2026-08-07T12:13:01.928369Z","title":"arXiv preprint arXiv:2309.01219","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:01.928369Z"},"links":{"cited_paper":"/paper/2309.01219","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:5566ee058c4d8a991ac8c3f6c9d6dabecfb19d500a835f2c0a1ac2dee623f58e","observation_id":"d79d1eb8-7a70-4ca9-843e-f76094eafb6d","resolution":{"observed_at":"2026-08-07T12:13:01.928369Z","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":"2026-08-07T12:13:03.273400Z","title":"B Experiment Details Datasets","venue":null,"work_id":"12c95a14-0cdd-415f-b107-c7dc169299d7","year":2023},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:02.002113Z"},"links":{"citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:087da781455adf64bcb59d1cab882330c4c84a6974afd1fc3fbcf1f7b82128d9","observation_id":"26f6aa2f-b6f3-42a9-b533-f03c3d746b7f","resolution":{"observed_at":"2026-08-07T12:13:03.333644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T12:13:03.006915Z","title":"Pretraining is conducted for 5 epochs using AdamW (Loshchilov and Hutter, 2017), with a batch size of 512 and a learning rate of 2e-5","venue":null,"work_id":"f4e2c1e2-2c9b-4db3-b59e-b7ad7809dbc9","year":2017},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:02.052058Z"},"links":{"citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:ab42fe5a5890616f4d785453478db79a2a9ae172eda6add9d6130046587f7b86","observation_id":"4bf68f7e-0f72-4c81-bf4e-2bbb873894b4","resolution":{"observed_at":"2026-08-07T12:13:03.141443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T12:13:02.507329Z","title":"C Potential Risk Although GPR demonstrates strong performance, it is still possible for the retrieved results to reflect biases","venue":null,"work_id":"986bf0f8-0692-4528-b447-dd071edbde09","year":2024},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:02.136813Z"},"links":{"citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:7ec18b3d4c7750eadb972a3835527c76d6138091d77bf09d7770d27582f5fd1f","observation_id":"7257f8eb-49dd-4b27-8a6c-9774f0b70da2","resolution":{"observed_at":"2026-08-07T12:13:02.697120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T12:13:03.591810Z","title":"In Proceedings of the 2008 ACM SIG- MOD international conference on Management of data, pages 1247–1250","venue":null,"work_id":"dcff51c6-355c-438d-bc52-25621df4b394","year":2008},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:59.441239Z"},"links":{"citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:ca5c06a04bf3813e15e74479ec0a33c283e0a8a5107f7503e1827076a150dcc9","observation_id":"42fac3f4-afe1-4a04-a6d4-7673c2cd9d5e","resolution":{"observed_at":"2026-08-07T12:13:03.665696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-07T12:13:00.477098Z","title":"arXiv preprint arXiv:1711.05101","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:00.477098Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:8569be04822b159acb9d222ae2a45268de22c48dac2e451a08a54420b402a2b9","observation_id":"2a461539-f2d3-49cc-a6ed-847040df1902","resolution":{"observed_at":"2026-08-07T12:13:00.477098Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.03748","last_updated":"2019-01-22T18:47:12Z","snapshot_observed_at":"2026-07-06T06:49:24.960992Z","submitted_at":"2018-07-10T16:52:11Z","title":"Representation Learning with Contrastive Predictive Coding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.03748","snapshot_observed_at":"2026-08-07T12:13:01.057421Z","title":"arXiv preprint arXiv:1807.03748","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:01.057421Z"},"links":{"cited_paper":"/paper/1807.03748","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:0c4ffc37756100ca24ec13f95c8724c3607ffa479b70e48dd8c9542cb4206961","observation_id":"a5f9e9fc-c6b3-4d6c-8eab-ef2dc815bdc0","resolution":{"observed_at":"2026-08-07T12:13:01.057421Z","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":"2026-08-07T12:13:03.423754Z","title":null,"venue":null,"work_id":"ffdb43ac-38d4-463f-940f-86b6e6d6d594","year":2019},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:59.634037Z"},"links":{"citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:f7050b8a9c2fd1b69a205c34e87de6afd818f18ed3757bd2a5183377b3f7bbe5","observation_id":"78550a01-e6ba-4c91-9dc9-8d4f5eb31c9d","resolution":{"observed_at":"2026-08-07T12:13:03.497374Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T12:13:02.808211Z","title":null,"venue":null,"work_id":"9c8283e3-8ec0-4019-9b88-16172e3cb0f5","year":2024},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:02.099792Z"},"links":{"citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:74a9f59cd74682685ac630cfa432061b3301e902deb8f91b48728ba5ff7d8ae3","observation_id":"c6f64b5d-a87f-4889-80bd-274ffbd07eb3","resolution":{"observed_at":"2026-08-07T12:13:02.931399Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T12:12:59.335089Z","title":"arXiv preprint arXiv:2303.08774","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:59.335089Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:202cb79b84d6a71003ee0b14ce97d4f186c19fc78e1f3985dbf564655fe5dfdf","observation_id":"8672aa27-eee8-456e-8062-6f3a5b554865","resolution":{"observed_at":"2026-08-07T12:12:59.335089Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T12:12:59.971190Z","title":"arXiv preprint arXiv:2407.21783","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:59.971190Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:e9931deeed2c5e5b0ef4acf9560772463125799f3defd7411e0572668f1c7b84","observation_id":"b2ea06af-eb16-4508-953e-bf15039fe5bf","resolution":{"observed_at":"2026-08-07T12:12:59.971190Z","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":"2026-08-07T12:13:01.822375Z","title":"arXiv preprint arXiv:2501.13958","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T12:13:01.822375Z"},"links":{"citing_paper":"/paper/2506.00261"},"observation_digest":"sha256:3c9de8aadac94d700555464d4af03438f685b09795c393a545c547ac365a4972","observation_id":"3b5bc858-fa54-460c-b0cc-90eb8dd418a0","resolution":{"observed_at":"2026-08-07T12:13:01.822375Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.00261","last_updated":"2025-06-03T02:07:40Z","latest_version":2,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-07T21:15:56.758416Z","submitted_at":"2025-05-30T21:50:29Z","title":"GPR: Empowering Generation with Graph-Pretrained Retriever"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":0,"verified_fuzzy":4},"total_outbound_references":24},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2506.00261."}