{"as_of":"2026-08-23T23:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bb1d5bed6a583615758cf7abd8ae373351228868ba903ed03daae02901fd07f7","coverage":[{"denominator":8,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":8,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-01T00:43:01.088339Z","state":"measured"},{"denominator":8,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":8,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2605.16309/citation-record","integrity":"/paper/2605.16309/integrity","json":"/paper/2605.16309/citation-record.json","paper":"/paper/2605.16309"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.03320","last_updated":"2025-06-03T19:06:41Z","snapshot_observed_at":"2026-08-17T00:30:22.493711Z","submitted_at":"2025-06-03T19:06:41Z","title":"The Future of Continual Learning in the Era of Foundation Models: Three Key Directions","version":1},"cited_work":{"arxiv_id":"2506.03320","doi":"10.48550/arxiv.2506.03320","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.03320","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"N., Li, L., Li, M., Madeddu, M., Piccoli, E., and Lomonaco, V","venue":"ArXiv.org","work_id":"eaff6e1c-b722-4330-a3e6-159a6ee746f8","year":2023},"citing_paper":{"arxiv_id":"2605.16309","last_updated":"2026-06-08T02:31:38Z","snapshot_observed_at":"2026-08-15T17:16:48.087948Z","submitted_at":"2026-05-04T05:24:03Z","title":"ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-01T00:43:01.088339Z"},"links":{"cited_paper":"/paper/2506.03320","citing_paper":"/paper/2605.16309"},"observation_digest":"sha256:7fa71147ea587ff4655a17485397d644886b9c58a5f75ff36fcc0d044a52b1f4","observation_id":"81347302-7a87-44b1-9386-a462bd02584b","resolution":{"observed_at":"2026-07-01T00:45:11.412770Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1145/3698590","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Minhua Lin, Hanqing Lu, Zhan Shi, Bing He, Rui Mao, Zhiwei Zhang, Zongyu Wu, Xianfeng Tang, Hui Liu, Zhenwei Dai, Xiang Zhang, Suhang Wang, Benoit Dumoulin, and Jian Pei","venue":"ACM Computing Surveys","work_id":"6749d77a-c63a-4871-bff9-3b902651e014","year":2026},"citing_paper":{"arxiv_id":"2605.16309","last_updated":"2026-06-08T02:31:38Z","snapshot_observed_at":"2026-08-15T17:16:48.087948Z","submitted_at":"2026-05-04T05:24:03Z","title":"ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-01T00:43:01.088339Z"},"links":{"citing_paper":"/paper/2605.16309"},"observation_digest":"sha256:3305669234702f20af752d14e1d27ecba47c9f064827dc5ed238ce18669712ff","observation_id":"f34014ba-5105-44f5-96da-91b7af62a180","resolution":{"observed_at":"2026-07-01T00:45:11.410219Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-07-07T08:13:30.896298Z","title":null,"venue":null,"work_id":"9afb0c98-5f8a-4132-be7f-80808da03658","year":null},"citing_paper":{"arxiv_id":"2605.16309","last_updated":"2026-06-08T02:31:38Z","snapshot_observed_at":"2026-08-15T17:16:48.087948Z","submitted_at":"2026-05-04T05:24:03Z","title":"ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-01T00:43:01.088339Z"},"links":{"citing_paper":"/paper/2605.16309"},"observation_digest":"sha256:5082078ef853d3d36b751dce015035dd41564eadf666eef9f23e9d80700ccf89","observation_id":"77b0e40a-e7e0-4412-83d0-b7dc933d25ee","resolution":{"observed_at":"2026-07-07T08:13:30.897299Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-07-07T08:13:30.901159Z","title":"Stage 2 uses few-shot constrained prompting to emit a patch in closed JSON schema","venue":null,"work_id":"af7bd244-af2f-4503-87df-3e2e690a6ebb","year":null},"citing_paper":{"arxiv_id":"2605.16309","last_updated":"2026-06-08T02:31:38Z","snapshot_observed_at":"2026-08-15T17:16:48.087948Z","submitted_at":"2026-05-04T05:24:03Z","title":"ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-01T00:43:01.088339Z"},"links":{"citing_paper":"/paper/2605.16309"},"observation_digest":"sha256:3b35f78e7f3ed35921d1fd6db86a1703bbdff6f44702ed68818d99c3051fa1f6","observation_id":"3696bf51-2f1e-489a-8560-9bc8ac2eccc7","resolution":{"observed_at":"2026-07-07T08:13:30.902322Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-07-07T08:13:30.897818Z","title":null,"venue":null,"work_id":"e81398bf-9da0-4429-9e0f-6e9f32b240c9","year":null},"citing_paper":{"arxiv_id":"2605.16309","last_updated":"2026-06-08T02:31:38Z","snapshot_observed_at":"2026-08-15T17:16:48.087948Z","submitted_at":"2026-05-04T05:24:03Z","title":"ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-01T00:43:01.088339Z"},"links":{"citing_paper":"/paper/2605.16309"},"observation_digest":"sha256:69c1ff334e5de4627563526949852f45d497dc4be0b5833bd5da30d19e9bc6e0","observation_id":"ea626032-0c52-4487-8d7e-997539a43894","resolution":{"observed_at":"2026-07-07T08:13:30.898991Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-07-07T08:13:30.894565Z","title":"5) evaluates plausibility, consistency, utility, and risk","venue":null,"work_id":"dea84d48-9f5c-489c-9378-bee946abc580","year":null},"citing_paper":{"arxiv_id":"2605.16309","last_updated":"2026-06-08T02:31:38Z","snapshot_observed_at":"2026-08-15T17:16:48.087948Z","submitted_at":"2026-05-04T05:24:03Z","title":"ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-01T00:43:01.088339Z"},"links":{"citing_paper":"/paper/2605.16309"},"observation_digest":"sha256:3517576aea199191fbbbdafd1ce49e299e0e5d70409c8cdccc928062a2270ed5","observation_id":"c7c77621-44a4-4ec3-8c59-5aee993dc67b","resolution":{"observed_at":"2026-07-07T08:13:30.895741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-07-07T08:13:30.899511Z","title":null,"venue":null,"work_id":"39d30321-7c3e-4874-8d17-1940f42db765","year":null},"citing_paper":{"arxiv_id":"2605.16309","last_updated":"2026-06-08T02:31:38Z","snapshot_observed_at":"2026-08-15T17:16:48.087948Z","submitted_at":"2026-05-04T05:24:03Z","title":"ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-01T00:43:01.088339Z"},"links":{"citing_paper":"/paper/2605.16309"},"observation_digest":"sha256:ce4f6685c949c58b8b6557e8565d17426a61a50e08b1a181a65e664c94407da1","observation_id":"4bf652c6-8f96-4c31-a67b-1cb2f7f73483","resolution":{"observed_at":"2026-07-07T08:13:30.900509Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-07-07T08:13:30.902876Z","title":"action a must complete within t seconds of b","venue":null,"work_id":"bd53c0ed-9536-42f3-a7b7-6b598c312de8","year":2025},"citing_paper":{"arxiv_id":"2605.16309","last_updated":"2026-06-08T02:31:38Z","snapshot_observed_at":"2026-08-15T17:16:48.087948Z","submitted_at":"2026-05-04T05:24:03Z","title":"ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-01T00:43:01.088339Z"},"links":{"citing_paper":"/paper/2605.16309"},"observation_digest":"sha256:59e1312595bc8b7a34ddc9e0e4b8097a63a91b13aba8411206e78b920b07d1ab","observation_id":"2688f9ff-8131-4feb-af2f-5f86b7c360fe","resolution":{"observed_at":"2026-07-07T08:13:30.903945Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.16309","last_updated":"2026-06-08T02:31:38Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-15T17:16:48.087948Z","submitted_at":"2026-05-04T05:24:03Z","title":"ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning"},"reference_resolution":{"displayed":8,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":1,"unresolved":2,"verified_exact":1,"verified_fuzzy":2},"total_outbound_references":8},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 8 of 8 outbound references and 0 inbound Pith citation observations for arXiv:2605.16309."}