{"as_of":"2026-08-20T15:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0cb3f3f0bcd3ce6c0d1c7d77d2a7f8a85ba8fecd9baab55d6f544e77bded8a91","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T19:31:45.949488Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T16:45:52.675056Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.16389","snapshot_observed_at":"2026-08-03T16:45:52.675056Z","title":"arXiv preprint arXiv:2506.16389 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28947","last_updated":"2026-07-31T02:05:45Z","snapshot_observed_at":"2026-08-17T03:28:09.745516Z","submitted_at":"2026-07-31T02:05:45Z","title":"Overcoming the Weakest-Link Effect in LLM-Driven Program Optimization via Heterogeneous Edit Recombination","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-03T16:45:52.675056Z"},"links":{"cited_paper":"/paper/2506.16389","citing_paper":"/paper/2607.28947"},"observation_digest":"sha256:fedae6479d70b66234e884d35b7371d5f431628db414efbbc51ed28477a6d427","observation_id":"6eb81169-c170-43a8-a0c4-552372f05d11","resolution":{"observed_at":"2026-08-03T16:45:52.675056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.16389/citation-record","integrity":"/paper/2506.16389/integrity","json":"/paper/2506.16389/citation-record.json","paper":"/paper/2506.16389"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:31:45.758106Z","title":"online\" 'onlinestring :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.758106Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:3416f77eeb7b2b547e261f71ec6a5ec192b3a61740b535ba9a7337fe0f341634","observation_id":"8e610697-3bf6-4b62-bb5a-e3f1f1b7c01f","resolution":{"observed_at":"2026-08-15T19:31:45.758106Z","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":"2026-08-15T19:31:45.762581Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.762581Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:1e5e6f6221475da9f906fff4b8d0f743aec8074f9322b6df7c9997aac59945dc","observation_id":"a0d31dc5-7672-4a9e-bd21-46d018fa1b9a","resolution":{"observed_at":"2026-08-15T19:31:45.762581Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-15T19:31:45.766296Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.766296Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:118681e0fc3b2a9673d23f1e0eb754dd2406012e233b348382cc5c458335b032","observation_id":"28fcdaad-5877-4aa9-9778-ea3d33870f76","resolution":{"observed_at":"2026-08-15T19:31:45.766296Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14423","last_updated":"2024-05-05T00:54:26Z","snapshot_observed_at":"2026-08-19T13:14:11.381268Z","submitted_at":"2024-01-24T06:20:18Z","title":"Prompt Design and Engineering: Introduction and Advanced Methods","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14423","snapshot_observed_at":"2026-08-15T19:31:45.769812Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.769812Z"},"links":{"cited_paper":"/paper/2401.14423","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:56df137ddc76524b4c6495efda5b29b2b47df9d3ea15fbe197ebd4ddaa6e0e31","observation_id":"3bc5d44a-6c76-477b-be99-a9d8510ebc1a","resolution":{"observed_at":"2026-08-15T19:31:45.769812Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13923","last_updated":"2025-02-19T18:00:14Z","snapshot_observed_at":"2026-08-14T04:17:22.593941Z","submitted_at":"2025-02-19T18:00:14Z","title":"Qwen2.5-VL Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13923","snapshot_observed_at":"2026-08-15T19:31:45.773548Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.773548Z"},"links":{"cited_paper":"/paper/2502.13923","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:18d2d71a1d672d4a604575bae738d199bdb87bd2eab689251c1579cc442ab825","observation_id":"aa5ca91b-8e28-4675-8add-a76398659e97","resolution":{"observed_at":"2026-08-15T19:31:45.773548Z","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":"2026-08-15T19:31:46.635171Z","title":null,"venue":null,"work_id":"b4d73c09-4616-4b32-a489-b2d35b4324ae","year":2006},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.777258Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:3654506679c17c6064ba1e12af5233013eeb924a35c7a3df91ffe779cdd19fe4","observation_id":"1cc2ecf1-bf59-471e-991a-ccd202e812fa","resolution":{"observed_at":"2026-08-15T19:31:46.638992Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07258","last_updated":"2022-07-12T23:45:14Z","snapshot_observed_at":"2026-08-02T09:20:40.804790Z","submitted_at":"2021-08-16T17:50:08Z","title":"On the Opportunities and Risks of Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07258","snapshot_observed_at":"2026-08-15T19:31:45.780747Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.780747Z"},"links":{"cited_paper":"/paper/2108.07258","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:458ccec0c1b01f3e5618d30ab1915a828ae55995a993ab230ea17eaa248b1e48","observation_id":"e6924f67-a593-4d91-8e10-79ccb582fb2e","resolution":{"observed_at":"2026-08-15T19:31:45.780747Z","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":"2026-08-15T19:31:45.784163Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.784163Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:e8941f2d24df36cb98088dab35ee5357becd6d7e44842b802ae3a8d895b3b63d","observation_id":"907d46a4-6f00-4e6b-a015-154d24875a40","resolution":{"observed_at":"2026-08-15T19:31:45.784163Z","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":"2026-08-15T19:31:45.787525Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.787525Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:1c25b56d84d2ca722dd0c309fdcda42ae9e71647608b8551a9848efdddd0102c","observation_id":"11b4a282-ee90-4e16-a0cc-e7e5e1c82a9c","resolution":{"observed_at":"2026-08-15T19:31:45.787525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13007","last_updated":"2024-06-21T19:34:27Z","snapshot_observed_at":"2026-08-19T13:14:39.854462Z","submitted_at":"2023-09-22T17:12:45Z","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13007","snapshot_observed_at":"2026-08-15T19:31:45.790562Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.790562Z"},"links":{"cited_paper":"/paper/2309.13007","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:5aa691004ae33de248c9f9ed0d77c32039d2701fbe9510de65703d24ef9db76a","observation_id":"7d8a1316-0b0b-4db2-bcd5-040503042c62","resolution":{"observed_at":"2026-08-15T19:31:45.790562Z","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":"10.1162/dint_a_00251","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:31:46.054005Z","title":null,"venue":null,"work_id":"4589900a-715e-449e-aaff-5ae58dae7de8","year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.794023Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:d90c9c70ffb8763ab9ce9e74092f55d65f3d9cd3b714f1956f5c3cff28451dc3","observation_id":"fb99ad81-d42f-4dda-8a52-5c6d746d5cd1","resolution":{"observed_at":"2026-08-15T19:31:46.057231Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-15T19:31:45.797511Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.797511Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:6a578646b20cd54a62448c3e0e07eb8a0844de1b7108e5540cf222698b1d4917","observation_id":"0216b504-969d-4c6d-b4fc-1b1d090acffc","resolution":{"observed_at":"2026-08-15T19:31:45.797511Z","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":"2026-08-15T19:31:45.800778Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.800778Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:afa0624a72292e08cd576931080b4c122280aacb2235ef7d006a7dd0ad6f6203","observation_id":"6e5945c8-649c-432e-b068-7a87d5ddad2c","resolution":{"observed_at":"2026-08-15T19:31:45.800778Z","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":"2026-08-15T19:31:45.804136Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.804136Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:008071787bffbebc1e12854d89c70251ad4daac69d7dd80d500f067dc7f6cd8f","observation_id":"80d3f998-c176-4ce3-8e00-b3ed7a21da5c","resolution":{"observed_at":"2026-08-15T19:31:45.804136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14325","last_updated":"2023-05-23T17:55:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-23T17:55:11Z","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14325","snapshot_observed_at":"2026-08-15T19:31:45.807266Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.807266Z"},"links":{"cited_paper":"/paper/2305.14325","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:83376e7d989cdfc9cbd19edb5b79a004d73b13755f7d97620dca0dadece0bbb0","observation_id":"2d19e590-529b-4c3c-b7aa-d31ce37229af","resolution":{"observed_at":"2026-08-15T19:31:45.807266Z","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":"2026-08-15T19:31:45.810753Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.810753Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:6f1fd0f55f225641d6ede0a53558693ef46b2d0ebca1622b59b377e333a46c42","observation_id":"5cb3ed5f-3454-4b69-8b50-736dd2487aeb","resolution":{"observed_at":"2026-08-15T19:31:45.810753Z","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":"2026-08-15T19:31:45.813714Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.813714Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:bcac51ac6a775ec83d45e804b333276a9eee1a26a487468e5e0e3df7bf74eff0","observation_id":"e843c297-2ef7-43d8-b251-ea889e14d796","resolution":{"observed_at":"2026-08-15T19:31:45.813714Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-15T19:31:45.816795Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.816795Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:ea1d1f088d9da2478209b46cc5dcc17c8bf7d429c4655dc80f719e0ddb7bf7ce","observation_id":"4586c3e4-d988-47e1-8fdc-45ab53f1beca","resolution":{"observed_at":"2026-08-15T19:31:45.816795Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.00805","last_updated":"2025-06-01T03:11:00Z","snapshot_observed_at":"2026-08-15T21:25:53.313888Z","submitted_at":"2025-06-01T03:11:00Z","title":"HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.00805","snapshot_observed_at":"2026-08-15T19:31:45.820094Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.820094Z"},"links":{"cited_paper":"/paper/2506.00805","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:31c9eed8ae21ed70f15e61a69769ad5d6cdbd5ae13618505dbbd3b8147c24a11","observation_id":"d4463c4a-fb36-4814-9e27-491ea0809502","resolution":{"observed_at":"2026-08-15T19:31:45.820094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.04514","last_updated":"2024-04-06T05:59:02Z","snapshot_observed_at":"2026-08-19T13:13:02.590745Z","submitted_at":"2024-04-06T05:59:02Z","title":"Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.04514","snapshot_observed_at":"2026-08-15T19:31:45.823618Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.823618Z"},"links":{"cited_paper":"/paper/2404.04514","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:4ef7ec073dc7e86bd1276eafeb2a4093922367687950a7bbb267e2da52a5f228","observation_id":"1080c5c9-fd64-4870-93b5-1fcb16b090cd","resolution":{"observed_at":"2026-08-15T19:31:45.823618Z","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":"10.18653/v1/2024.findings-emnlp.221","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T19:31:46.019964Z","title":null,"venue":null,"work_id":"cc22d622-835a-42c4-a7e1-be389deb82b7","year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.827428Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:202a1183a69f71529e3c766a6c88407c2255b4970b11af195d45ade547068087","observation_id":"c82160b8-5af3-4656-824b-20c2587fc7ab","resolution":{"observed_at":"2026-08-15T19:31:46.024945Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.00806","last_updated":"2025-06-01T03:15:29Z","snapshot_observed_at":"2026-08-09T07:52:39.727951Z","submitted_at":"2025-06-01T03:15:29Z","title":"Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering","version":1},"cited_work":{"arxiv_id":"2506.00806","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.00806","snapshot_observed_at":"2026-08-15T19:31:46.251633Z","title":"Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering","venue":"cs.CL","work_id":"d110abca-0c8b-4c4d-83f9-a6dda56e4050","year":2025},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.830484Z"},"links":{"cited_paper":"/paper/2506.00806","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:17ce1e1e82d06c71601eb402b58e1a24b2d7552a0c041b3a6836abdcb387e80f","observation_id":"109e3e8d-2ec2-418f-be28-f26ef0ed8efa","resolution":{"observed_at":"2026-08-15T19:31:46.257862Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:45.833514Z","title":"Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.833514Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:759a2d795402683755ef9a89534e735d4323623d4d3fe3e161553b71f1c098e0","observation_id":"870ccefd-442c-43ac-b57e-c7e21f25ef76","resolution":{"observed_at":"2026-08-15T19:31:45.833514Z","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":"2026-08-15T19:31:46.606620Z","title":null,"venue":null,"work_id":"813914cb-a3b4-4618-8528-d36e4c49241e","year":2017},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.836900Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:e39ac74f98a9851ffcbe2de2753ec3d02f8e6845b75e59464a23ee519f2b2b50","observation_id":"01d4d6af-ce18-4cb1-9e54-9c1cabe1b573","resolution":{"observed_at":"2026-08-15T19:31:46.610327Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:46.596458Z","title":null,"venue":null,"work_id":"94a7d9d7-bfdb-4475-83ba-669c8c00e92b","year":2017},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.840058Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:3defba3ce4f30b8e411a65a8eb6c962bff928efdbef14ce25ef5036b7f0958df","observation_id":"be6b5984-29a6-4c36-8877-1477550db522","resolution":{"observed_at":"2026-08-15T19:31:46.599824Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:45.843611Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.843611Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:e7e24820d2e56b9fffeaa4906005dfe4c12191b6e18e832b8812a4b04cd85eb7","observation_id":"6c01a146-8e5f-4296-af8f-9bd233657b82","resolution":{"observed_at":"2026-08-15T19:31:45.843611Z","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":"2026-08-15T19:31:45.846830Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.846830Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:a2403d27a8312b65ea4dab25a473c069d01ab5bd65eee3566db65efea98dfa64","observation_id":"b624b63d-2b62-42bb-b3e6-d1ad9cd84454","resolution":{"observed_at":"2026-08-15T19:31:45.846830Z","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":"2026-08-15T19:31:45.850413Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.850413Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:d0250ff5c46bcf0e60648a0ffae4a5dc5b6e3e6349c9fa2a565b11e9cb07d9de","observation_id":"0e6fd5a0-1f98-41bc-9705-a21a6f9db3e7","resolution":{"observed_at":"2026-08-15T19:31:45.850413Z","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":"2026-08-15T19:31:45.853885Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.853885Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:ebbb599a6cb21e5b803237fc5bed862166db483219d07d50025fbe534cc2390b","observation_id":"b6322f43-bb35-485f-acd8-219fccc30b61","resolution":{"observed_at":"2026-08-15T19:31:45.853885Z","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":"2026-08-15T19:31:45.857169Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.857169Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:b190b3b414121e7eecba22d3776815f2a0c1c2b82abd35c5ca56bba7d7baa667","observation_id":"c57ae881-6dc1-4bdb-9e09-32184778a402","resolution":{"observed_at":"2026-08-15T19:31:45.857169Z","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":"2026-08-15T19:31:46.569175Z","title":null,"venue":null,"work_id":"6f7bcfcc-463a-4131-a6d2-55976c1b7c11","year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.860325Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:ab531f0e219a216a8da9aa89190907c5743281bd0e5a91ee4c2db8aa4a5bf363","observation_id":"de616ca2-3a2e-4bf4-bd41-81113285d108","resolution":{"observed_at":"2026-08-15T19:31:46.572507Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:46.558829Z","title":null,"venue":null,"work_id":"65a393bb-16a0-4ce5-9f27-e8199c38ef44","year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.863482Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:f9bac6258320539f4e919f5e406acf98a0ae95ce1f17dd8a9f5a26284e7b9357","observation_id":"094ffda6-ed60-4c6b-adb7-b00906c3e61d","resolution":{"observed_at":"2026-08-15T19:31:46.562087Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:46.548510Z","title":null,"venue":null,"work_id":"c16aada2-54be-429b-ad2e-aa600b776fd1","year":2019},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.866955Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:59082b2b1e1ed0c02dc103389cbd5cd567a1cf5034e80c4b8e69ebced2d0a984","observation_id":"cfbd30df-3ca6-4a0e-baa5-0fa6599984d3","resolution":{"observed_at":"2026-08-15T19:31:46.551885Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:45.870488Z","title":null,"venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.870488Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:bcd46f5d22b95b1bcca408be6f93a6d10ba2c97e9c0a795366f8b462700971ce","observation_id":"997f95f4-8ba1-4ffb-b407-2050ad914edc","resolution":{"observed_at":"2026-08-15T19:31:45.870488Z","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":"2026-08-15T19:31:46.531733Z","title":null,"venue":null,"work_id":"e6c29598-44d2-4d09-b5de-6f5164ce042d","year":2022},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.873863Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:a0df2a16be1d09d0ab5ea4db13572edf7f4557512ce011d8656fe766b94d7d24","observation_id":"5b929d0a-528f-4b13-ba7e-f13549b65d39","resolution":{"observed_at":"2026-08-15T19:31:46.535631Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:46.520393Z","title":null,"venue":null,"work_id":"ed8a2648-93e7-4b2d-b6f0-e1f6ef999801","year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.877510Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:1e96fddec21f4e3b668ede37cf43e81876f0878c95f61be6f45ffeb5d91cbe05","observation_id":"a7b01451-3324-456a-8ab5-6df512863277","resolution":{"observed_at":"2026-08-15T19:31:46.524588Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:46.509206Z","title":null,"venue":null,"work_id":"1479c6bf-4127-40a5-ac65-374017cabbcd","year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.880658Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:b083a7107fb6b85eab465cf538e2a4b39f5476524e6729e8ca4c6c45b52e96f1","observation_id":"734fa178-f266-4f25-9fc7-d64f24b5e962","resolution":{"observed_at":"2026-08-15T19:31:46.513136Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:45.883957Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.883957Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:1eabf76dc97eca76eace1b01f7cd34e4004b42e12e713e068e3f3b762364fd93","observation_id":"3efc940c-0817-4d4a-912f-24d55298fe6c","resolution":{"observed_at":"2026-08-15T19:31:45.883957Z","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":"2026-08-15T19:31:45.887284Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.887284Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:478d771c4ff2774ca8f40234fb098f0e04e441ce5b3ff1e6b778ee4e88fd50ab","observation_id":"343877ef-e834-4b6d-974d-5a73ebf91312","resolution":{"observed_at":"2026-08-15T19:31:45.887284Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18865","last_updated":"2024-02-29T05:27:45Z","snapshot_observed_at":"2026-08-19T13:14:10.280946Z","submitted_at":"2024-02-29T05:27:45Z","title":"Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18865","snapshot_observed_at":"2026-08-15T19:31:45.890490Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.890490Z"},"links":{"cited_paper":"/paper/2402.18865","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:0058fccb996ca4c72034057654443f63609b6c2c1301a6402ce2a54efaf226b7","observation_id":"89fa8134-619e-4c66-9114-dc06363a3d01","resolution":{"observed_at":"2026-08-15T19:31:45.890490Z","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":"2026-08-15T19:31:45.894068Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.894068Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:d6bedac94de217f6396599cae9c5e733cd5676a8db3a21403ec5f5d8860de10d","observation_id":"ffca3082-0cad-4563-a3bb-15d72fff56e3","resolution":{"observed_at":"2026-08-15T19:31:45.894068Z","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":"2026-08-15T19:31:46.493841Z","title":null,"venue":null,"work_id":"209e6001-4683-439d-b12a-569ea9c56411","year":2022},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.897196Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:f1a81f4d5fdab1ca9a842788b69419fc5ce83c45a9a6806e1b6e691ea819b581","observation_id":"7fc72af8-b4e2-47df-b007-de946efae97b","resolution":{"observed_at":"2026-08-15T19:31:46.497162Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:45.900368Z","title":null,"venue":null,"work_id":null,"year":1948},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.900368Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:eeb9569677fc7c9199ca34f305f96803cd2a1a17ce0590e6ffe24d2cf53b8e90","observation_id":"4a262a7e-713f-4db1-bd69-b5fbe5fbd903","resolution":{"observed_at":"2026-08-15T19:31:45.900368Z","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":"2026-08-15T19:31:45.904108Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.904108Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:5eb50f366fbea37609588dcfe94ee6a80b5599115d3b3fa8c2976ef4e8a73d32","observation_id":"271724bd-457b-4b63-9682-1bc262afdb87","resolution":{"observed_at":"2026-08-15T19:31:45.904108Z","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":"2026-08-15T19:31:45.907287Z","title":"Logan IV, Eric Wallace, and Sameer Singh","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.907287Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:9d83a7ea550acb3d5c8777e3e27f93410d23cd77cc81fce9d7926b7cfbf7a947","observation_id":"5bda2dbf-e7e3-483e-a6c3-590b3105451e","resolution":{"observed_at":"2026-08-15T19:31:45.907287Z","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":"2026-08-15T19:31:46.478506Z","title":null,"venue":null,"work_id":"7be86f28-3095-4b34-ba60-1a018c175d6d","year":2012},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.910568Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:95ed03f7c61d699e4d9399c9a90e94e99c0d5b28d4f1b128e2b6a1dc95d0177f","observation_id":"490beb2c-7dfe-4335-8a3b-3f19a55a00cb","resolution":{"observed_at":"2026-08-15T19:31:46.481762Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:46.468657Z","title":null,"venue":null,"work_id":"c265f350-9180-4ea6-9cbd-bb9cce2d9084","year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.913628Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:97888b8392e6a6150eae0cd8cbb775d9a63c704e5e93612b5c62e12661705bd9","observation_id":"1fe9d177-3fe8-4c77-a4b7-ba64bb9a8a2e","resolution":{"observed_at":"2026-08-15T19:31:46.472030Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:45.916740Z","title":"Le, Ed H","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.916740Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:0c4e7d7cc9ccb7d210e23daecaa2b1118d25aa1990e5def4cad719b4732745f2","observation_id":"1586c3a0-6589-4dd1-b44e-a0b937b3fb15","resolution":{"observed_at":"2026-08-15T19:31:45.916740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05530","last_updated":"2024-12-16T17:39:39Z","snapshot_observed_at":"2026-08-14T18:15:53.516440Z","submitted_at":"2024-03-08T18:54:20Z","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05530","snapshot_observed_at":"2026-08-15T19:31:45.919962Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.919962Z"},"links":{"cited_paper":"/paper/2403.05530","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:944ec7d24ffcd6f3ed9f0d8f2fe30b5cfa626072f1b47714d0aee0975bee1d30","observation_id":"7cee1a38-c5a6-4b36-8b7f-5ada18703b50","resolution":{"observed_at":"2026-08-15T19:31:45.919962Z","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":"2026-08-15T19:31:45.923136Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.923136Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:08e2703c986c98d41f86a71f95cf6c7560cb838822f08e7d4a3806dbbf3b27b7","observation_id":"fafc36a0-1079-4fdb-a0f5-123a6ce95a9f","resolution":{"observed_at":"2026-08-15T19:31:45.923136Z","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":"2026-08-15T19:31:46.452204Z","title":null,"venue":null,"work_id":"4b173fc3-cc61-428b-bb7f-492f1c72f21b","year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.926112Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:6a4d6e3515518b7695337482c7bab863edbbfa21dca02608908a4c6626f1741d","observation_id":"c85a1188-0e51-4cae-bb46-4d0b025a4c69","resolution":{"observed_at":"2026-08-15T19:31:46.455618Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:45.929390Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.929390Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:dd3057a876f9557716a5d785b79f5712418988650c9d66db3a68e28dce41ac42","observation_id":"0794c232-5134-4773-805b-17b955cff406","resolution":{"observed_at":"2026-08-15T19:31:45.929390Z","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":"2026-08-15T19:31:46.441316Z","title":"Le, Denny Zhou, and Xinyun Chen","venue":null,"work_id":"efd375d5-ae25-4bcb-ada4-ea84b1ed39ef","year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.932905Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:a515279fe35dbe200255a63805d381a7b952c452a3b6e397bf87f225f38ae1b3","observation_id":"3bec112d-0dfe-44be-ae1a-4dbf36229e10","resolution":{"observed_at":"2026-08-15T19:31:46.445207Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:45.936244Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.936244Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:51954c14a4ca1cbcb7df68c106cb1f14413b3186b85dcac5c02507e43dfaeeb3","observation_id":"cd2f1f92-3a52-4011-b491-5c459c6a696a","resolution":{"observed_at":"2026-08-15T19:31:45.936244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07496","last_updated":"2024-06-11T17:32:21Z","snapshot_observed_at":"2026-08-13T02:15:58.634561Z","submitted_at":"2024-06-11T17:32:21Z","title":"TextGrad: Automatic \"Differentiation\" via Text","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07496","snapshot_observed_at":"2026-08-15T19:31:45.939560Z","title":"differentiation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.939560Z"},"links":{"cited_paper":"/paper/2406.07496","citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:fb81f6a69e58c23daf49ef70118ceb32ac15d76a7ce658eccabeeaf808b95251","observation_id":"a2555c2a-630c-4426-bea2-91fc1a15d667","resolution":{"observed_at":"2026-08-15T19:31:45.939560Z","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":"2026-08-15T19:31:46.423626Z","title":"Gonzalez","venue":null,"work_id":"dced2577-067d-462f-a58e-bcf11e15a7ae","year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.943296Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:314c05594990ac8d2ce41cb1b97d4d51ef1d84d9a73d1f2e0c341096adae5283","observation_id":"160d7530-86fe-496a-8da7-746c82caed49","resolution":{"observed_at":"2026-08-15T19:31:46.427698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T19:31:45.946396Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.946396Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:bebb485e3d6e9f5dbd360c7ee37420464d69a1e388e73ee9f5eb46743cf3941f","observation_id":"3c8831f7-84a3-44ee-8608-7958dec3dcf1","resolution":{"observed_at":"2026-08-15T19:31:45.946396Z","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":"2026-08-15T19:31:45.949488Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-15T19:31:45.949488Z"},"links":{"citing_paper":"/paper/2506.16389"},"observation_digest":"sha256:34bcd140b6d8d28307fd3d687119112997a1321c2d2ce99fc8627ab9c7f4f4fd","observation_id":"8dbb3197-f4f8-4523-99e4-01cea3d4b12b","resolution":{"observed_at":"2026-08-15T19:31:45.949488Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.16389","last_updated":"2025-06-19T15:19:56Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-17T22:17:58.892530Z","submitted_at":"2025-06-19T15:19:56Z","title":"RiOT: Efficient Prompt Refinement with Residual Optimization Tree"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":52,"verified_exact":3,"verified_fuzzy":2},"total_outbound_references":58},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2506.16389."}