{"as_of":"2026-08-15T13:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b352156d3b1de7cc06c14009bb78d5b76788eb4b441d93af29d59675dfcad5be","coverage":[{"denominator":18,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":18,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T09:42:49.752547Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2607.24791/citation-record","integrity":"/paper/2607.24791/integrity","json":"/paper/2607.24791/citation-record.json","paper":"/paper/2607.24791"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T09:42:49.676084Z","title":"Retrieval- Augmented Generation for Knowledge- Intensive NLP Tasks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.676084Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:eea0c181e29481f57a113d9b335b06b5488a832299ad9dae1a716602e6c833a0","observation_id":"60eb218e-d5a0-4d2d-a5cd-11f70159806d","resolution":{"observed_at":"2026-08-02T09:42:49.676084Z","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":"2026-08-02T09:42:49.681154Z","title":"Question -Based Retrieval Using Atomic Units for Enterprise RAG,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.681154Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:b2ea81828757acb40345fbff9c65a5ddb061f7a4466ec5497a66863149787e7f","observation_id":"44d49e11-1a32-4546-8f29-2cf4ed7651e0","resolution":{"observed_at":"2026-08-02T09:42:49.681154Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07321","last_updated":"2025-06-12T03:39:58Z","snapshot_observed_at":"2026-08-12T23:25:23.619099Z","submitted_at":"2024-07-10T02:33:09Z","title":"Benchmarking LLMs for Environmental Review and Permitting","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07321","snapshot_observed_at":"2026-08-02T09:42:49.685666Z","title":"RAG vs. Long Context: Examining Frontier Large Language Models for Environmental Review Document Comprehen- sion,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.685666Z"},"links":{"cited_paper":"/paper/2407.07321","citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:2bf7828c45b87e241f8c4d1e4e8d7fcb2f88f1c2234f440b8416fc303764f5cc","observation_id":"8d864654-ec3d-4c48-925d-e721fe4d5ea4","resolution":{"observed_at":"2026-08-02T09:42:49.685666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00090","last_updated":"2024-08-26T08:17:42Z","snapshot_observed_at":"2026-08-12T22:57:36.318206Z","submitted_at":"2024-08-26T08:17:42Z","title":"Evaluating ChatGPT on Nuclear Domain-Specific Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.00090","snapshot_observed_at":"2026-08-02T09:42:49.690596Z","title":"Evaluating ChatGPT on Nuclear Domain - Specific Data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.690596Z"},"links":{"cited_paper":"/paper/2409.00090","citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:1110db69e6ca101c1a51c407b88da7dac8ddc9cf541c232ca855300d79378e92","observation_id":"11037d4a-4008-4086-a51c-4a5f9960a4ee","resolution":{"observed_at":"2026-08-02T09:42:49.690596Z","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":"2026-08-02T09:42:49.695220Z","title":"Lost in the Middle: How Language Models Use Long Contexts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.695220Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:d74b94353e1a6d4c45918a88d3659266c5cef6ce58945424c57a5f9097349336","observation_id":"39f9acc7-0283-4a13-9b79-2690232f9e7b","resolution":{"observed_at":"2026-08-02T09:42:49.695220Z","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":"2026-08-02T09:42:49.699313Z","title":"Prompt Compression for Large Language Models: A Survey,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.699313Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:7d120d7f327658bf2d38363aaa2012caf84d3291a06d9b4ae15bafe05470c991","observation_id":"90d518a5-d6d3-4bd2-b7a4-7b74025b981d","resolution":{"observed_at":"2026-08-02T09:42:49.699313Z","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":"2026-08-02T09:42:49.704241Z","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.704241Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:02fb242dededb140a31c3a4eaa785c7d051b5842a20ef7ed083de1b088513572","observation_id":"3e268800-482e-431c-abf0-93b0b739e6dd","resolution":{"observed_at":"2026-08-02T09:42:49.704241Z","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":"2026-08-02T09:42:49.708308Z","title":"Toolformer: Language Models Can Teach Themselves to Use Tools,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.708308Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:31d684c3447f36ca2083a67adc2bce3b125bdb0ab21ec4815dcb65ca2a0272df","observation_id":"cbbbbe6a-df0b-406e-b335-6f3028177875","resolution":{"observed_at":"2026-08-02T09:42:49.708308Z","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":"2026-08-02T09:42:49.712386Z","title":"ReAct: Synergizing Reasoning and Acting in Language Models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.712386Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:66e6dd2c9607348dc22f616fc78ea88804aaba7cb3a8198512aca91706cf652b","observation_id":"4d90e1f4-aa75-438d-9839-5c28ffe55ff6","resolution":{"observed_at":"2026-08-02T09:42:49.712386Z","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":"2026-08-02T09:42:49.716708Z","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.716708Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:d93ab76eebe479486e6f83f58e465f084c5c8d6387bbc44dd12c0b84acc045ec","observation_id":"ecdf345f-e575-45a9-9ee5-e5c077362152","resolution":{"observed_at":"2026-08-02T09:42:49.716708Z","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":"2026-08-02T09:42:49.720944Z","title":"Interaction with Texts: Information Retrieval as Information-Seeking Behavior,","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.720944Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:20464d7e7b4509618290f7fcfdb66453b8444bba2e2db6e5bb01b6f91a687fec","observation_id":"76a45171-a27f-43bc-bfed-6fbce8b59aba","resolution":{"observed_at":"2026-08-02T09:42:49.720944Z","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":"2026-08-02T09:42:49.725175Z","title":"Information Foraging,","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.725175Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:b219840059888c4a24ae23b4e667034dc4fde80b3dccab21d67eab36857ba6c4","observation_id":"e7216b99-efff-4228-abec-ba5de4769500","resolution":{"observed_at":"2026-08-02T09:42:49.725175Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09136","last_updated":"2026-04-01T15:51:06Z","snapshot_observed_at":"2026-08-07T12:36:27.102579Z","submitted_at":"2025-01-15T20:40:25Z","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09136","snapshot_observed_at":"2026-08-02T09:42:49.729663Z","title":"Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.729663Z"},"links":{"cited_paper":"/paper/2501.09136","citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:9b2f1a687f70ce25a12af10093d2ee9d260dcff68e0b81c79d3f8b2de2687e50","observation_id":"9b66708d-297c-4b9d-b94a-ed3837556748","resolution":{"observed_at":"2026-08-02T09:42:49.729663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.08757","last_updated":"2025-06-10T12:55:07Z","snapshot_observed_at":"2026-08-14T10:26:07.711121Z","submitted_at":"2025-06-10T12:55:07Z","title":"Enhancing Accuracy and Maintainability in Nuclear Plant Data Retrieval: A Function-Calling LLM Approach Over NL-to-SQL","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.08757","snapshot_observed_at":"2026-08-02T09:42:49.734207Z","title":"Enhancing Accuracy and Maintainability in Nuclear Plant Data Retrieval: A Function -Calling LLM Approach Over NL-to-SQL","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.734207Z"},"links":{"cited_paper":"/paper/2506.08757","citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:6a3c16578cc003b3677c2bfee6c329711f0d6837d1923be4dc50854b6eed277c","observation_id":"5ae6c16d-dbc1-4415-b788-8ad0353a6708","resolution":{"observed_at":"2026-08-02T09:42:49.734207Z","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":"2026-08-02T09:42:49.738753Z","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval- Augmented Generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.738753Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:e44764bf54d845a65b4965c24b4fb5bd343cc7b49fe68083eee5ad3d346f717d","observation_id":"0589a018-6530-4b9b-a1d6-a484819711ec","resolution":{"observed_at":"2026-08-02T09:42:49.738753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00091","last_updated":"2024-08-26T08:21:21Z","snapshot_observed_at":"2026-08-12T22:57:35.952573Z","submitted_at":"2024-08-26T08:21:21Z","title":"Classification of Safety Events at Nuclear Sites using Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.00091","snapshot_observed_at":"2026-08-02T09:42:49.743000Z","title":"Classification of Safety Events at Nuclear Sites using Large Language Models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.743000Z"},"links":{"cited_paper":"/paper/2409.00091","citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:3443fa9a3b00e1d1df0bb66d54588b880f91152b06dc3e8f5de0f3d7ad8b1457","observation_id":"091fcc7c-92a8-4818-b180-0b6762d831d6","resolution":{"observed_at":"2026-08-02T09:42:49.743000Z","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":"2026-08-02T09:42:49.747900Z","title":"Automating equipment identification in nuclear engineering drawings","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.747900Z"},"links":{"citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:c3f6528e379f7afd29f2ab423342b54e06964069c55151e5f4849028fe0dbfc6","observation_id":"f1458f22-b45d-4279-9fd2-e5717e2a803a","resolution":{"observed_at":"2026-08-02T09:42:49.747900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.08746","last_updated":"2025-06-10T12:40:47Z","snapshot_observed_at":"2026-08-13T08:57:45.472371Z","submitted_at":"2025-06-10T12:40:47Z","title":"Towards Secure and Private Language Models for Nuclear Power Plants","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.08746","snapshot_observed_at":"2026-08-02T09:42:49.752547Z","title":"Towards Secure and Private Language Models for Nuclear Power Plants","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T09:42:49.752547Z"},"links":{"cited_paper":"/paper/2506.08746","citing_paper":"/paper/2607.24791"},"observation_digest":"sha256:fd655304b528fb0cfdcf4e12a06905c1a58a09085c653c3db8a3f8099272f57d","observation_id":"a3bf0296-cce4-4bd0-9e07-b65e1952c3d2","resolution":{"observed_at":"2026-08-02T09:42:49.752547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.24791","last_updated":"2026-06-28T14:11:03Z","latest_version":1,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-10T22:37:56.680220Z","submitted_at":"2026-06-28T14:11:03Z","title":"From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance"},"reference_resolution":{"displayed":18,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":18},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2607.24791."}