{"as_of":"2026-08-18T04:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:57a1a93afa1185613809f19c6663ac2a97ac6fd6a3bce98f73f4754af244c816","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T22:04:47.044235Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T18:10:42.575529Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-11T18:11:28.051623Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.25920","snapshot_observed_at":"2026-08-04T15:12:55.609877Z","title":"2026 , archivePrefix =","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.02097","last_updated":"2026-08-03T11:58:21Z","snapshot_observed_at":"2026-08-15T22:59:26.336051Z","submitted_at":"2026-08-03T11:58:21Z","title":"Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-04T15:12:55.609877Z"},"links":{"cited_paper":"/paper/2605.25920","citing_paper":"/paper/2608.02097"},"observation_digest":"sha256:5dbeaddbed7a3a8da477bb39696f82ae78ad2b7444c09e2e281fe8c4d60516d1","observation_id":"2646a657-42d2-4521-bbc8-9f7279738551","resolution":{"observed_at":"2026-08-04T15:12:55.609877Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2605.25920","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.25920","snapshot_observed_at":"2026-08-11T18:11:28.051623Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","venue":"cs.CL","work_id":"40f7fd58-b8df-45dc-88ef-c29fe4e03c7d","year":2026},"citing_paper":{"arxiv_id":"2608.09393","last_updated":"2026-08-10T10:20:13Z","snapshot_observed_at":"2026-08-17T05:06:20.473106Z","submitted_at":"2026-08-10T10:20:13Z","title":"Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T18:10:42.575529Z"},"links":{"cited_paper":"/paper/2605.25920","citing_paper":"/paper/2608.09393"},"observation_digest":"sha256:378920b28acd8da06acef4d830c7facf90ca2745a1d86fcadd7c32186b2b1a96","observation_id":"6e97d099-dca3-4b21-a432-d5deac563ed8","resolution":{"observed_at":"2026-08-11T18:11:28.057574Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2605.25920/citation-record","integrity":"/paper/2605.25920/integrity","json":"/paper/2605.25920/citation-record.json","paper":"/paper/2605.25920"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2508.12281","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T22:14:00.357816Z","title":"Legalδ: Enhancing legal reasoning in llms via reinforcement learning with chain-of-thought guided information gain","venue":null,"work_id":"1b57acf1-137d-458b-a0a3-6b60261314e7","year":2024},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:02acd8abc22e27b95dd058780e449d2f299af6344939d18dc9ea19e3f45ed721","observation_id":"193a4f38-f9dc-418d-a489-6f642894242a","resolution":{"observed_at":"2026-06-29T22:14:00.359419Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2510.12979","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T22:14:00.363573Z","title":"Zhiwei Fei, Xiaoyu Shen, Dawei Zhu, Fengzhe Zhou, Zhuo Han, Songyang Zhang, Kai Chen, Zongwen Shen, and Jidong Ge","venue":null,"work_id":"27f79560-5e81-41c4-9ba0-c5edb7270e60","year":2023},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:8ecddb96e57ddec1dc753b94259eeb9af03005262af6263bd0dd165c3222879c","observation_id":"09f45f7e-2fe8-4630-b71a-9bd5a814adca","resolution":{"observed_at":"2026-06-29T22:14:00.365370Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.01840","last_updated":"2025-04-25T01:57:31Z","snapshot_observed_at":"2026-08-16T12:44:32.601403Z","submitted_at":"2025-04-02T15:45:03Z","title":"LRAGE: Legal Retrieval Augmented Generation Evaluation Tool","version":2},"cited_work":{"arxiv_id":"2504.01840","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.01840","snapshot_observed_at":"2026-06-29T22:14:00.360833Z","title":"InProceedings of the 38th AAAI Conference on Arti- ficial Intelligence, pages 18642–18650","venue":null,"work_id":"fa2def49-7839-4cd2-b057-5744f4aaf89e","year":2025},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"cited_paper":"/paper/2504.01840","citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:7098f574a15497084e0b7062f71cb120b21ef5b7990fbd62ace43a64e983201f","observation_id":"2ab5190a-7f3a-4fdf-a308-c312f2a8e6c6","resolution":{"observed_at":"2026-06-29T22:14:00.362373Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":"2505.09388","doi":"10.1016/j.aiopen.2022.12","metadata_source":"pith","pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Qwen3 Technical Report","venue":"cs.CL","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","year":2025},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:443137ffcfc2fdce093ff1fc39ecbbffa0f52dd10e948b1484a4f11731eb2918","observation_id":"b36a8c1a-e9bd-4595-80b8-029f14fb3205","resolution":{"observed_at":"2026-06-29T22:14:00.367766Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04614","last_updated":"2024-06-07T03:52:56Z","snapshot_observed_at":"2026-08-16T13:45:17.991452Z","submitted_at":"2024-06-07T03:52:56Z","title":"LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model","version":1},"cited_work":{"arxiv_id":"2406.04614","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04614","snapshot_observed_at":"2026-07-03T16:48:39.805985Z","title":"entities","venue":null,"work_id":"fee9ed10-3ef9-4003-b1f8-f350a00a1801","year":2024},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"cited_paper":"/paper/2406.04614","citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:200c36ac7faebef39b14f77a4534ae71332b18545e0728cabead7d3700059caf","observation_id":"4bf34098-d542-457d-9032-ea46efde9337","resolution":{"observed_at":"2026-06-29T22:14:00.370449Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-06-29T22:04:47.044235Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:c6caf5b3adf92e4dcf229966963b9b82d9a9a02ff14296b1068b3ca12cf5d454","observation_id":"173019d4-33b5-4283-993d-bb378bbb95c3","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:e40b931fb333ef51978f1c86cd041f5103a0d04efe1d134689626445ae89f2b1","observation_id":"2193ce8c-6040-4244-b05f-b541df178913","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":"Tool Routing Rules","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:e56f48061527e6ac3028c8a17be79e0a9da49bc752902e7c5d930efa246c8047","observation_id":"bd0f1d24-7ae5-4570-bf6f-5360ddfdcc06","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":"Article X","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:eb8caa89e48a23f2f95782ce7fc729cb2d41d7e7193deec7da2efefa4dcf4851","observation_id":"a0bdadbe-efb1-4c02-b29e-24d4bbcaeca6","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":"Figure 7: System prompt used during training and evaluation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:614e16fd67a08d51cd4271aa377523beef1d73ff454fefe07fefb636c4fd1f5f","observation_id":"9dd3068e-da8a-4c8e-8f26-24784aa90cb2","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:07deef2767258434b51b67fff2ab0d7b252cda73c8f8e903e95512d2e6db90e6","observation_id":"9a22c327-bd0b-4747-8bb8-985917b8dff1","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:36e9cb149e901e2cc081ea3bba1c4fae26ec6ac2bb2a3213c002122d0811127a","observation_id":"e603c4ab-bac9-4bee-9af6-59454e2766e7","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:cb19cdc0b83ff4d64a98c364079d303e27a567588651cedda710b83e70b23a75","observation_id":"6de1b9b8-b75c-4da3-b31b-8fd527cc594d","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":"5.Scholarly interpretations, academic viewpoints, controversies, and expert opinionsshould all be extracted","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:1007ef0bc94d6807a46e53ebfdee5a4b06b193909fc9a871df1785db5a610ff9","observation_id":"db195121-3434-49db-a978-99ae04b06396","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":"2024” → [","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:9f8e0b04618ccaa193464b0d4e3627fef127bb3dfa1a2d5eb8eab4209e87f36c","observation_id":"65e7d17a-d3f0-4fbe-a190-6d8271fb62cd","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":"Article X","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:c3ac0ee86165537a270b0e82f0be6815d9102a1a9cfca61f56157c9b09e784a7","observation_id":"be39cf13-929f-4911-873a-f585f9468251","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":"intentional homicide","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:d6a143ee49693988b7b73b1ba10aa47a357e3f2b932c7b8de9f08c27de19c02a","observation_id":"858b9622-492c-4a06-aed9-a975a533e635","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:6b352539957b27c22059566da7a990299b4d5566a2b4d4067f457b6399e430d2","observation_id":"fffec87c-373b-443f-986a-7219e6d8df26","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","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":"2026-06-29T22:04:47.044235Z","title":"name\": \"web_search","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-29T22:04:47.044235Z"},"links":{"citing_paper":"/paper/2605.25920"},"observation_digest":"sha256:a60672f298d28e1a6a035f17ad888a90768cc665d19cc6ebb73d1179360d1fba","observation_id":"f9871d9a-770c-406a-af92-db03c46d755f","resolution":{"observed_at":"2026-06-29T22:04:47.044235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2605.25920","last_updated":"2026-05-25T14:57:13Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-03T08:30:36.070554Z","submitted_at":"2026-05-25T14:57:13Z","title":"Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":1,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":14,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":19},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 2 inbound Pith citation observations for arXiv:2605.25920."}