{"as_of":"2026-08-09T23:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6e4338d302ed956fe51b8e9e1ebecb587cda2f7b24ce73eb2445ee8ebeb24af2","coverage":[{"denominator":21,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":21,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:09:55.024301Z","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":"2026-08-09T06:31:02.800959+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/2507.06396/citation-record","integrity":"/paper/2507.06396/integrity","json":"/paper/2507.06396/citation-record.json","paper":"/paper/2507.06396"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:09:54.924681Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.924681Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:b3ba6689a4c27b68f5e8a9ef1aa7ad29ac10b82076381c5a9d58d354e36281a1","observation_id":"6b6b91be-d877-4ec7-bb3d-24a6aa243384","resolution":{"observed_at":"2026-08-06T19:09:54.924681Z","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":"2026-08-06T19:09:55.558245Z","title":"LiteLLM , July 2025","venue":null,"work_id":"712ccc78-5d33-41de-9eca-b1f17b4206af","year":2025},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.928563Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:89a240dbaf78c9e6bda10df0a3762b9f0d5d5533292bdd5be3120c53f5ac6647","observation_id":"d4008108-a7fc-41a7-b8f9-1184e09be96b","resolution":{"observed_at":"2026-08-06T19:09:55.561461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.546253Z","title":"Prompting is programming: A query language for large language models","venue":null,"work_id":"5399d505-81c3-4460-973a-67d5e7a2239a","year":1946},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.931924Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:86043fdad77a3ccae5f4818d408b7cbf286f9bb6350b3165f26f42d277f48de2","observation_id":"c7bcde13-d36d-4153-865a-fad7d6aae29d","resolution":{"observed_at":"2026-08-06T19:09:55.549614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.534563Z","title":null,"venue":null,"work_id":"2ea1fe34-a6e9-4cf7-a6e7-36a58b6b7674","year":2025},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.936017Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:ca60921eded78f28613713bebc54abc693e6cf9851c0e1044bcdd52d40566a99","observation_id":"5ecaaff6-f825-430f-8557-a12f86ab2782","resolution":{"observed_at":"2026-08-06T19:09:55.538479Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.523050Z","title":null,"venue":null,"work_id":"14025460-96f1-460e-9b1c-2f2899e8f439","year":2025},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.939483Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:428cfe7f861ab216dda98a9d1ddb8c656f7d2e6cbfea070bbcdebfc52ca266a7","observation_id":"47df0a6d-9680-4a0f-b142-3ddf63fc9e9c","resolution":{"observed_at":"2026-08-06T19:09:55.526791Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.512294Z","title":"V., Haq, S., Sharma, A., Joshi, T","venue":null,"work_id":"8c7ca6af-fd3e-486a-a004-3495da3a83a7","year":2024},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.942846Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:2579a3d544b0a9f258cc325cd8542f3ecf7a70dd51c979272a8aae9e7465a84e","observation_id":"09144daa-df83-4281-b3bf-7ec592b03740","resolution":{"observed_at":"2026-08-06T19:09:55.515349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.500231Z","title":null,"venue":null,"work_id":"5e53d2a9-aa46-4cac-9510-dea97eda2e03","year":2005},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.946722Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:1ce59cf15a9c20ce20f9633026871a94ac71ec5b10c62f8c16920ff8f3938e8f","observation_id":"a2afae97-5249-4027-95ab-c89a57b7bd1f","resolution":{"observed_at":"2026-08-06T19:09:55.504163Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.488351Z","title":"Llama Stack , July 2025","venue":null,"work_id":"770da420-7580-407d-b155-8f6468c9ba47","year":2025},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.950408Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:8bfb71cdd3d4c837e991a526a29145479f9ed472dc5df820e925c3ddc8540572","observation_id":"63856d38-74ea-4f77-b273-ccea65800dc5","resolution":{"observed_at":"2026-08-06T19:09:55.492349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.476513Z","title":"\\ guidance\\ : A guidance language for controlling large language models, July 2025","venue":null,"work_id":"083667a9-183b-4fc1-9571-19b119dde3e4","year":2025},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.953496Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:bc5079a65a4ea7e314ac4429f9d8023eafa514074486c5c1c0523af9e259e19e","observation_id":"76ed587e-ff7c-49d0-8950-516728ed4f2b","resolution":{"observed_at":"2026-08-06T19:09:55.480529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.464508Z","title":"CrewAI : Framework for orchestrating role-playing, autonomous AI agents, July 2025","venue":null,"work_id":"845c465c-a1b8-4220-956a-efdbdafd7576","year":2025},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.957828Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:6ac4cb4bc611fd444d1e9034e4f75141c695d81ba328822c79342920d0b0530f","observation_id":"23e6fb8b-5b91-4457-bff7-d58e7ba8f8fb","resolution":{"observed_at":"2026-08-06T19:09:55.468399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.450863Z","title":"L., Suarez, F., Ugarte, M., and Vrgo c , D","venue":null,"work_id":"3f8fbe9a-6670-49ae-87af-5ab8b88e239a","year":2016},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.961337Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:b75e8a394473fd7c5c300040ae485c7f59f3886ab4130d65730f561fd6074401","observation_id":"8bfc16b7-634b-4eb2-b4d4-ef49cedabd80","resolution":{"observed_at":"2026-08-06T19:09:55.455436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.388329Z","title":"and Zhang, B","venue":null,"work_id":"f341cbbd-647f-4e3c-a458-1222093fd8f0","year":2025},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.964560Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:7ab7755de90fc105bf43725d2198fcca5055421ead5e1414b510bcae39bd6fc8","observation_id":"98c37564-ced8-4ee3-a564-ea3826c24054","resolution":{"observed_at":"2026-08-06T19:09:55.439924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.220474Z","title":"AutoPDL : Automatic prompt optimization for LLM agents","venue":null,"work_id":"acb7d3bf-74e4-471e-a236-a93f771ec264","year":2025},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.969811Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:2dc167ee9f60a43e68937314215f1c3d32dfb717461e31b751c36a7b8c4fbc12","observation_id":"834af8cb-fca4-4540-8b4e-fea8ff6d914c","resolution":{"observed_at":"2026-08-06T19:09:55.247992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19135","last_updated":"2024-10-24T20:07:08Z","snapshot_observed_at":"2026-07-06T19:39:23.839070Z","submitted_at":"2024-10-24T20:07:08Z","title":"PDL: A Declarative Prompt Programming Language","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19135","snapshot_observed_at":"2026-08-06T19:09:54.974620Z","title":"PDL : A declarative prompt programming language, October 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.974620Z"},"links":{"cited_paper":"/paper/2410.19135","citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:7caad84711f32dcd2bd6cede2364ee59605ea2a372c0b25845ea1f08441f4fae","observation_id":"13340d43-2857-4c93-883c-5473ada702e0","resolution":{"observed_at":"2026-08-06T19:09:54.974620Z","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":"2026-08-06T19:09:55.172925Z","title":"Chain-of-thought prompting elicits reasoning in large language models","venue":null,"work_id":"9a715fa7-791f-47e1-8b95-962161b4c944","year":2022},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.980408Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:fc687b4f961c70772595740e65290dc4138d18d72b3777e3a72be887ba96660d","observation_id":"2be797c0-2f30-4cdc-ba86-022099d2abe1","resolution":{"observed_at":"2026-08-06T19:09:55.192423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09702","last_updated":"2023-08-19T21:27:51Z","snapshot_observed_at":"2026-08-09T04:46:02.275866Z","submitted_at":"2023-07-19T01:14:49Z","title":"Efficient Guided Generation for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09702","snapshot_observed_at":"2026-08-06T19:09:54.987291Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.987291Z"},"links":{"cited_paper":"/paper/2307.09702","citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:991a7868a7900e39af0863557d3a88b62da3dfa0150450a3a5299d1464d281c4","observation_id":"501b3037-ce44-4726-939c-47efc781a8c8","resolution":{"observed_at":"2026-08-06T19:09:54.987291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08155","last_updated":"2023-10-03T20:47:10Z","snapshot_observed_at":"2026-08-08T22:28:26.004138Z","submitted_at":"2023-08-16T05:57:52Z","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.08155","snapshot_observed_at":"2026-08-06T19:09:54.993112Z","title":"H., White, R","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:54.993112Z"},"links":{"cited_paper":"/paper/2308.08155","citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:85032ef79415281a1433122971b469fb23e2fc00dd12e5dfc807a75f890c45bb","observation_id":"ff64b672-e2bd-4df3-b538-635470adf725","resolution":{"observed_at":"2026-08-06T19:09:54.993112Z","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":"2026-08-06T19:09:55.129856Z","title":"Decoupling reasoning from observations for efficient augmented language models, September 2023","venue":null,"work_id":"549fc6ad-cb3f-4166-9446-8ded0d822721","year":2023},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:55.000274Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:4641c0356ea3421a2be329aa7d2dee886bc67d4b6bf833c4fcd8f229eb61c1fb","observation_id":"c305f644-475d-43b4-b410-5311ba94d224","resolution":{"observed_at":"2026-08-06T19:09:55.145682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T19:09:55.114782Z","title":"R., and Cao, Y","venue":null,"work_id":"b6601484-54da-4f58-8785-1ae8c55e366b","year":2023},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:55.010077Z"},"links":{"citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:702e26b97bc820d6fe2c73f1ebab48e7160eb6be515216817f6e4a15f31de3be","observation_id":"352b6747-d306-407b-a752-31bb8340876f","resolution":{"observed_at":"2026-08-06T19:09:55.119500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14228","last_updated":"2025-03-10T02:42:01Z","snapshot_observed_at":"2026-08-03T14:04:24.986841Z","submitted_at":"2024-06-20T11:49:23Z","title":"EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14228","snapshot_observed_at":"2026-08-06T19:09:55.016338Z","title":"EvoAgent : Towards automatic multi-agent generation via evolutionary algorithms, July 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:55.016338Z"},"links":{"cited_paper":"/paper/2406.14228","citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:cf8af108899420cec567c017a29cf42651d6347ec8c8b3596825e93fd3c69ac0","observation_id":"5d15497b-ae09-421c-886d-17e40a87c272","resolution":{"observed_at":"2026-08-06T19:09:55.016338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.07104","last_updated":"2024-06-06T00:10:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-12T09:34:27Z","title":"SGLang: Efficient Execution of Structured Language Model Programs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.07104","snapshot_observed_at":"2026-08-06T19:09:55.024301Z","title":"H., Cao, S., Kozyrakis, C., Stoica, I., Gonzalez, J","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T19:09:55.024301Z"},"links":{"cited_paper":"/paper/2312.07104","citing_paper":"/paper/2507.06396"},"observation_digest":"sha256:f9a3e277b10d5c8913d5e13abf3fd3a96ee5c48f15aca010d826cb8052b16281","observation_id":"5c336b28-40f2-4ac4-971b-ba4dcbe9e320","resolution":{"observed_at":"2026-08-06T19:09:55.024301Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.06396","last_updated":"2025-07-08T21:03:22Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-06T19:03:35.606723Z","submitted_at":"2025-07-08T21:03:22Z","title":"Representing Prompting Patterns with PDL: Compliance Agent Case Study"},"reference_resolution":{"displayed":21,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":12},"total_outbound_references":21},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2507.06396."}