{"as_of":"2026-08-09T13:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aff0f11f8d692316659e78b236962ba860721b392fd96b46ec45f3ce01f7d3ad","coverage":[{"denominator":76,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":76,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:59:51.806810Z","state":"measured"},{"denominator":78,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":78,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T11:07:31.861143Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-30T11:24:38.808622Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"cited_work":{"arxiv_id":"2505.20266","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.20266","snapshot_observed_at":"2026-06-30T11:24:38.808622Z","title":"syftr: Pareto-optimal generative ai, 2025","venue":null,"work_id":"9c2c37a1-aec0-44c5-9a27-f73d2b4c4cf8","year":2025},"citing_paper":{"arxiv_id":"2605.27361","last_updated":"2026-05-26T17:58:47Z","snapshot_observed_at":"2026-08-04T13:19:25.137063Z","submitted_at":"2026-05-26T17:58:47Z","title":"Natural Language Query to Configuration for Retrieval Agents","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T17:44:34.509337Z"},"links":{"cited_paper":"/paper/2505.20266","citing_paper":"/paper/2605.27361"},"observation_digest":"sha256:171996186d6f918cbbd12b624f27ebee3c2705ea50cce7e664792ed75af70df7","observation_id":"a9c8c68f-9eec-46ae-8fe6-6e12e0862631","resolution":{"observed_at":"2026-06-29T17:53:47.651781Z","resolver_source":"arxiv_id","status":"verified_exact"},"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":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"cited_work":{"arxiv_id":"2505.20266","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.20266","snapshot_observed_at":"2026-06-30T11:24:38.808622Z","title":"syftr: Pareto-optimal generative ai, 2025","venue":null,"work_id":"9c2c37a1-aec0-44c5-9a27-f73d2b4c4cf8","year":2025},"citing_paper":{"arxiv_id":"2606.28365","last_updated":"2026-06-14T16:59:18Z","snapshot_observed_at":"2026-07-07T00:02:29.000757Z","submitted_at":"2026-06-14T16:59:18Z","title":"CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-30T11:07:31.861143Z"},"links":{"cited_paper":"/paper/2505.20266","citing_paper":"/paper/2606.28365"},"observation_digest":"sha256:146467bbd2fb4e608fded4af0a706d84a273c6cf3aac5bdf439c99ce52257790","observation_id":"53f385e5-d021-4225-afd9-fd9d61fe58d2","resolution":{"observed_at":"2026-06-30T11:24:38.809966Z","resolver_source":"arxiv_id","status":"verified_exact"},"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"}}],"links":{"evidence":"/evidence","html":"/paper/2505.20266/citation-record","integrity":"/paper/2505.20266/integrity","json":"/paper/2505.20266/citation-record.json","paper":"/paper/2505.20266"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:00:00.710918Z","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks, 2021","venue":null,"work_id":"1e9af086-bf57-4682-9ef6-99c025383d32","year":2021},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:46.984191Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:25a21dd32e14436c6b2d233db90939e043c735abc6294cdd8fce0c0fc8123447","observation_id":"995d4abd-f6d5-4b83-a472-5a3e04501e40","resolution":{"observed_at":"2026-08-07T14:00:00.765966Z","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":"2026-08-07T14:00:00.613489Z","title":"Retrieval augmenta- tion reduces hallucination in conversation","venue":null,"work_id":"1955fade-5e27-4373-9da4-287458b0f155","year":2021},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.023725Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:9d8e8b3550a270c2903f49d0fdd1121701de43d66693c2343eadae4f04e337bb","observation_id":"199de09e-1b4e-48a0-84bb-818fc6484f32","resolution":{"observed_at":"2026-08-07T14:00:00.624270Z","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":"2026-08-07T14:00:00.492121Z","title":"Realm: retrieval- syftr 11 augmented language model pre-training","venue":null,"work_id":"14386def-4566-45f6-a878-ec4dbdaeb476","year":2020},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.082378Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:70068d1b5bd71a3229a0ae34a12170656e68698bab7e80c0431551ef55d8dcad","observation_id":"9a521cc4-586d-496a-b09c-b9ec234d0bde","resolution":{"observed_at":"2026-08-07T14:00:00.556722Z","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":"2026-08-07T14:00:00.400708Z","title":"Improving language models by retrieving from trillions of tokens","venue":null,"work_id":"2471a26f-e0ae-4d69-80a6-cb362f2d7629","year":2022},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.138286Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:91e0e6508455b7b8a13e264b7be8744d1a8009a1ce44dd8980946cd30ab823cd","observation_id":"9eb7f412-3e4b-4dc7-a384-2353f4d09d23","resolution":{"observed_at":"2026-08-07T14:00:00.449026Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:47.181513Z","title":"LangChain, October 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.181513Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:9c6ec1d4bfa27b212987366a8c51f05c8745ee7eaa19863e60f41eb89dfb44e0","observation_id":"8828bde9-97e7-42d0-8895-36182a52af2d","resolution":{"observed_at":"2026-08-07T13:59:47.181513Z","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":"2026-08-07T13:59:47.256879Z","title":"Autogen: Enabling next-gen llm applications via multi-agent conversation, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.256879Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:ee84ffa895429ceb2e8297bbc9b73fe214072519434ad2c961df576bed0b292f","observation_id":"092059da-7689-431c-9c4a-8774ef47a6bd","resolution":{"observed_at":"2026-08-07T13:59:47.256879Z","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":"2026-08-07T14:00:00.301025Z","title":"Haystack: the end-to-end NLP framework for pragmatic builders, November 2019","venue":null,"work_id":"df38c05a-0644-4211-93d8-c88fdd7926b9","year":2019},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.323650Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:24b806738202907933288ea81ffdafa15a1e2300c1971f9a7735d12e76bfd51c","observation_id":"c9e5c769-cbeb-41d1-853a-15b3a4bc352f","resolution":{"observed_at":"2026-08-07T14:00:00.335913Z","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":"2026-08-07T14:00:00.195872Z","title":"crewAI: Collaborative Research and Workflows AI, 2023","venue":null,"work_id":"7cfafa27-f833-48e8-bb9a-359dc6c1be64","year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.397105Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:5d8fc4c2fba0280b051107f9b3335c3daf293d63add8f1c4eb40ada0b2e8c856","observation_id":"3358227e-5919-4797-93ee-8cd26705c4f2","resolution":{"observed_at":"2026-08-07T14:00:00.256369Z","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":"2026-08-07T14:00:00.077004Z","title":"LlamaIndex, November 2022","venue":null,"work_id":"ed639d09-8ae2-437f-8ff0-0893422962ca","year":2022},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.475867Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:970fbc5a12bd253144b3b8f8323edef276d29fc717a30f9799bc6af2d31d6267","observation_id":"8f56ac98-12fc-48a4-a346-fa179ce55866","resolution":{"observed_at":"2026-08-07T14:00:00.138865Z","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":"2026-08-07T13:59:59.964678Z","title":"Approximate nearest neighbor search in high dimensions, 2018","venue":null,"work_id":"6b2d5fc9-4e77-46a5-916b-3215607f01b0","year":2018},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.544830Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:345a2bdd6304235dcf89c1f7ea16e0170220c5829aae5bc7d8bea95a6e455424","observation_id":"0b2b353e-358f-41bc-b243-35556984a618","resolution":{"observed_at":"2026-08-07T14:00:00.000725Z","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":"2026-08-07T13:59:59.878677Z","title":"Mteb: Massive text embedding benchmark, 2023","venue":null,"work_id":"b01f1e6d-44a0-4078-97f6-7caf0fa761fd","year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.602318Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:e51325ef0fc1dffb428a3e79a125b420303b9708b0af51b5a827da8fac049820","observation_id":"4e02dc95-6b0d-40cd-9dd1-6b156d703552","resolution":{"observed_at":"2026-08-07T13:59:59.919875Z","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":"2026-08-07T13:59:59.801953Z","title":"Chonkie: A fast feature-full chunking library for rag bots","venue":null,"work_id":"eefda90e-2309-4d99-a27c-6e68f9f2c302","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.652038Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:83238b211479bcbc884db3fecf138c34fdbcf57e144a3ad7dcccea1257302f80","observation_id":"a6f5d13a-931c-4d6b-a08b-9d2fcab34774","resolution":{"observed_at":"2026-08-07T13:59:59.855469Z","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":"2026-08-07T13:59:59.690676Z","title":"The probabilistic relevance framework: Bm25 and beyond","venue":null,"work_id":"f1b0b585-accf-49b5-841a-9a46da7c08c5","year":2009},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.699979Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:890f3f09719d813a72e2f1b025a9259bd84a7881ba18ab363fac865cd9c5c4f6","observation_id":"28b670ae-7b95-4c15-9647-089e855592eb","resolution":{"observed_at":"2026-08-07T13:59:59.732630Z","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":"2026-08-07T13:59:59.571046Z","title":"Rag-fusion: A new take on retrieval augmented generation","venue":null,"work_id":"1c7ae7b5-62c3-4535-99ec-6710dd7469bd","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.749034Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:c5c7691db53b67eaeb79bfbed046609f153442caab20d2d50d6699f516f71419","observation_id":"18764bb6-44f2-4b4d-8e88-343514ab4b50","resolution":{"observed_at":"2026-08-07T13:59:59.615815Z","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":"2026-08-07T13:59:59.351643Z","title":"Pinecone: A vector database for machine learning applications, 2025","venue":null,"work_id":"d9e3ff6f-ed8d-45ad-ac2f-f4f543915378","year":2025},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.805571Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:04cc5253e645490ee0b9cb6592ae0b4412db356a786facbfd31876e2340886c4","observation_id":"65cc7c46-ec49-45ff-a148-73978872f9a7","resolution":{"observed_at":"2026-08-07T13:59:59.465038Z","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":"2026-08-07T13:59:59.149860Z","title":"The faiss library, 2024","venue":null,"work_id":"e894ef64-5786-4147-94e2-17e2e7da8e26","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.856992Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:694788671fd3f40419ad0f3eac839c6cd9c5fecd91426ecb14cb42a78b9b87b4","observation_id":"14f05be3-01aa-40e4-927f-7818b135406c","resolution":{"observed_at":"2026-08-07T13:59:59.253694Z","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":"2026-08-07T13:59:58.939602Z","title":"Neo4j: The World’s Leading Graph Database","venue":null,"work_id":"c05ca7c6-ba66-4933-932b-9aa833f2666d","year":null},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.920057Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:8b28ece47887d77827cdd6c51bbc08851c48eb194d77cdaf4be4fd538e1b9a8c","observation_id":"d9836632-2ed3-4e97-bd58-042cbcb6ccb2","resolution":{"observed_at":"2026-08-07T13:59:59.060133Z","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":"2026-08-07T13:59:58.786590Z","title":"Agentic retrieval- augmented generation for time series analysis, 2024","venue":null,"work_id":"ee8ce0dd-ae0b-4f5e-be1c-df6c5acc1e34","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:47.965057Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:67df2bd6da94f0d6c58a579e1ef79a156cffcf14995ec791dfe48b483c3a9a26","observation_id":"d0428f33-b313-4e00-ae45-98d93fc9f1d2","resolution":{"observed_at":"2026-08-07T13:59:58.824579Z","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":"2026-08-07T13:59:58.645449Z","title":"Building a rag pipeline is difficult, 2024","venue":null,"work_id":"9e245773-2950-4446-a2c6-cf74f150ecfd","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.035601Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:c86163be12eec2efc0d2ecd3adbcda5998cfbc1b7cf38681ac80662bfff288f7","observation_id":"35f4ddb4-5ee8-4fd8-9b62-20b3d0cc920d","resolution":{"observed_at":"2026-08-07T13:59:58.737544Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:48.076823Z","title":"Large language models are better reasoners with self-verification, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.076823Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:9014e6f7a0cf51d94010b44d6d32ac3d5a3dd51bf49de743be39798021b55256","observation_id":"a0b8e1da-dbf4-43e8-9041-1768e8e35f69","resolution":{"observed_at":"2026-08-07T13:59:48.076823Z","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":"2026-08-07T13:59:58.468074Z","title":"Precise zero-shot dense retrieval without relevance labels, 2022","venue":null,"work_id":"56c70960-e73e-4d2d-b323-e4a9feb5c1ee","year":2022},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.116267Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:43195b25f18dd4ad0e7afd2617dcaf4bba9fd312b1ab8eb452235e2230fa6fbe","observation_id":"9ad522b2-f168-4cc3-87e7-4d83577e0d14","resolution":{"observed_at":"2026-08-07T13:59:58.548992Z","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":"2026-08-07T13:59:58.345460Z","title":"Re2g: Retrieve, rerank, generate, 2022","venue":null,"work_id":"5a1dcd6c-86a1-464f-8fa6-21228fe46a7b","year":2022},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.195100Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:91c52c1062c7b9b8e3f961e6f958c9ec26dee74d317ee3f8d8254632c5d3ab9b","observation_id":"845d5855-028c-4052-a9e4-b74c88806be8","resolution":{"observed_at":"2026-08-07T13:59:58.404067Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:48.265442Z","title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.265442Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:3eb60d801ce0b03e0d8d52fba6f90851ab6c7c448acb69a0dbd2cf5f17417f7d","observation_id":"dff8469f-17b9-4cc1-a41a-bb33870807db","resolution":{"observed_at":"2026-08-07T13:59:48.265442Z","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":"2026-08-07T13:59:48.343030Z","title":"Convex Optimization","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.343030Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:c4b2e601151c0cda79ef808afaa5db69c740cea7c7eb971dafc8463d993defac","observation_id":"273f91dd-72b9-4007-b9af-cec4002f514e","resolution":{"observed_at":"2026-08-07T13:59:48.343030Z","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":"2026-08-07T13:59:48.388187Z","title":"Bayesian Optimization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.388187Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:4e243b246308cb73140957133b24ce5174811551ece6e01735c578220ae68975","observation_id":"0f34bf25-1e0f-456e-947d-4e72e521eccc","resolution":{"observed_at":"2026-08-07T13:59:48.388187Z","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":"2026-08-07T13:59:58.179932Z","title":"Automated Machine Learning - Methods, Systems, Challenges","venue":null,"work_id":"2df856ca-ed4c-439a-a78c-6c92809c4472","year":2019},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.469169Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:8859f50edde3ef5f08350ae835fdc21d97ceade0e89e39531c1515c1b0213a20","observation_id":"52b34707-b99b-4521-ab90-98a92e77b789","resolution":{"observed_at":"2026-08-07T13:59:58.259774Z","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":"2026-08-07T13:59:58.029935Z","title":"Auto-sklearn 2.0: Hands-free automl via meta-learning, 2022","venue":null,"work_id":"41100ecc-2192-4de0-a302-13d980fbdee4","year":2022},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.537773Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:9827a1b11c0dcc200c920127368849741c9c0eaace5a760ec99291596e8d29e0","observation_id":"d3e19857-a0f4-4ef7-84bb-b311dc520cef","resolution":{"observed_at":"2026-08-07T13:59:58.113062Z","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":"2026-08-07T13:59:57.880013Z","title":"Datarobot: Automated machine learning, 2012","venue":null,"work_id":"17561554-8c39-42da-9af2-13d03f426642","year":2012},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.653708Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:32b50848fdb7f6181fc3b0f7858dedf5d2d10d35b014a9029a9a33cb66d74f7b","observation_id":"002dcf6d-df1a-4fc0-bb67-33f5ee451c96","resolution":{"observed_at":"2026-08-07T13:59:57.953681Z","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":"2026-08-07T13:59:57.640945Z","title":"On hyperparameter optimization of machine learning algorithms: Theory and practice","venue":null,"work_id":"6f995dcf-c756-4a2e-9665-753bc48bdb56","year":2020},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.708112Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:09288d70aa1965843e7a2d03c27a6823f71c5be660bb97a8f56c4b1672c99c22","observation_id":"9a54dceb-814a-4466-90ca-93d81d9f3ddb","resolution":{"observed_at":"2026-08-07T13:59:57.758229Z","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":"2026-08-07T13:59:57.389799Z","title":"Neural architecture search: Insights from 1000 papers, 2023","venue":null,"work_id":"e5139473-897c-4434-8ba9-272420b6b99d","year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.790931Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:55ede6d559e2391a94df84f17a3e1bb94045fa2b05a2cc54f8bce6d21cb403ce","observation_id":"8573372d-fa14-449f-a803-10c14e089f3b","resolution":{"observed_at":"2026-08-07T13:59:57.496274Z","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":"2026-08-07T13:59:57.132279Z","title":"Litetransform- ersearch: Training-free neural architecture search for efficient language models","venue":null,"work_id":"72f1a1b7-a791-4c27-9e31-178d4be595d9","year":2022},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.836458Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:b73c99ad8861934456746750e7241814334f3d5618f3d10759efe55f8d77ea17","observation_id":"01d13afe-19c9-4c7b-9a41-0c0306de9e92","resolution":{"observed_at":"2026-08-07T13:59:57.296000Z","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":"2026-08-07T13:59:56.890830Z","title":"Advancing the accuracy-efficiency frontier with llama 3.1 and nemotron 51b, 2024","venue":null,"work_id":"57d23ce4-4a8d-41ea-a09f-3de4ee40baa9","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:48.925991Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:79883886aafc1cc3619cf08299fc8a1827a90c24b66e3ba993452526ffe28f5d","observation_id":"c8bcb3a5-9d33-4953-a557-cd707a4224ab","resolution":{"observed_at":"2026-08-07T13:59:57.011096Z","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":"2026-08-07T13:59:56.666246Z","title":"Autorag: Automated framework for optimization of retrieval augmented generation pipeline, 2024","venue":null,"work_id":"1af76b8a-e92c-4365-a98a-e8809f485d85","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.001132Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:948a2aafe78c86feab1ef851fe7bc42abde30f5eb948768fdf4846444ec5f04b","observation_id":"78cc0303-0340-4bcd-a48a-2d01799331ed","resolution":{"observed_at":"2026-08-07T13:59:56.751587Z","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":"2026-08-07T13:59:56.440619Z","title":"Learning In Modular Systems","venue":null,"work_id":"998cdc0a-4e4a-4c47-93da-fe4165931928","year":2010},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.071578Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:a5c872484b4dfaaa28f47a306e7d488c67a85daf7a288660e3086b8c29b6f0b8","observation_id":"ce1da914-f54e-4217-820b-82ae426db07a","resolution":{"observed_at":"2026-08-07T13:59:56.566172Z","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":"2026-08-07T13:59:56.282049Z","title":"Metareasoning in modular software systems: On-the-fly configuration using reinforcement learning with rich contextual representations","venue":null,"work_id":"955f7534-b7a7-4dd7-b3d5-13b1bc8c6f05","year":2020},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.210092Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:58e6d6912aaa2e79bd089d4a3a489d4abe55951566dd4c33370e52430c3a65a4","observation_id":"2575748e-6f6c-4b9f-b209-ca3e80d02512","resolution":{"observed_at":"2026-08-07T13:59:56.358796Z","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":"2026-08-07T13:59:56.101962Z","title":"Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts","venue":null,"work_id":"2e3c6938-9f40-42ef-bc60-f698ff85d966","year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.328552Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:55f82768491489682a8fda98310612731f689bc574cce30434160e36c1bba813","observation_id":"e3e865dd-64c1-489d-9cb6-1aba571b13aa","resolution":{"observed_at":"2026-08-07T13:59:56.195222Z","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":"2026-08-07T13:59:55.860576Z","title":"Trace is the next autodiff: Generative optimization with rich feedback, execution traces, and llms, 2024","venue":null,"work_id":"7ab1398e-b9c8-4ffd-9557-57cc6b655ff8","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.454947Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:569ee1fd6fa2ae78519cb7855c5ec452863dcadb737b7bab50724858f0347d3a","observation_id":"2c9dee95-58e3-430a-bc22-dda93e5a2578","resolution":{"observed_at":"2026-08-07T13:59:55.996808Z","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":"2406.07496","last_updated":"2024-06-11T17:32:21Z","snapshot_observed_at":"2026-07-06T18:29:04.294349Z","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":"2026-08-07T13:59:49.533177Z","title":"Textgrad: Automatic” differentiation” via text","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.533177Z"},"links":{"cited_paper":"/paper/2406.07496","citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:03a14f35436ab9e910d7c5364c7c867dd19c3243494bfe61efa56035aa4a94ac","observation_id":"8f0ce5b0-a0fb-40d1-a120-c140725a3b51","resolution":{"observed_at":"2026-08-07T13:59:49.533177Z","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":"2026-08-07T13:59:49.617604Z","title":"Le, Denny Zhou, and Xinyun Chen","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.617604Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:cbe9619a27827a84e446b3ba127d948ca218c38e2bf694c461007683e3337aa0","observation_id":"d1440616-81bc-40b9-aae4-c599b3cb454b","resolution":{"observed_at":"2026-08-07T13:59:49.617604Z","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":"2026-08-07T13:59:55.604431Z","title":"Parameswaran, and Eugene Wu","venue":null,"work_id":"b3b21b6a-b3fa-449e-bd0e-1c097a642485","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.689667Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:362d2fe9d7fe92b053e8563ef649ade2dda7a4ef18e475608c90661fb4aaca39","observation_id":"e715c4a7-8da2-4488-873a-f12c12c189a8","resolution":{"observed_at":"2026-08-07T13:59:55.712645Z","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":"2026-08-07T13:59:55.419700Z","title":"The cascades framework for query optimization","venue":null,"work_id":"ff94cbd4-fe89-4dba-b72a-2a4c1c4ce31f","year":1995},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.732974Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:491af3b4e4893dc6f994e227901afb868d7006b646d5a48be495fb498d3e99ac","observation_id":"8debd2f4-ae34-472f-a10c-7803e62d694a","resolution":{"observed_at":"2026-08-07T13:59:55.502216Z","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":"2026-08-07T13:59:55.251151Z","title":null,"venue":null,"work_id":"cdfc04ac-51a1-4c0e-a071-9b8e6437e499","year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.784725Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:2ddb06d31c4abbc8ad04bac0e1c7ce6186e2a311e04e4c58c085de137fa71e6c","observation_id":"e22c9cb0-9245-464d-ae6d-94f8156d9c0e","resolution":{"observed_at":"2026-08-07T13:59:55.310287Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:49.836836Z","title":"Critic: Large language models can self-correct with tool-interactive critiquing, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.836836Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:3f9547b7901ba6f33e48251afd13e3dc0df6b988ff261c3d78aa6ce0a3f3ac7a","observation_id":"1a504291-2b26-4ba8-a429-d4efd211a1b6","resolution":{"observed_at":"2026-08-07T13:59:49.836836Z","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":"2026-08-07T13:59:49.875177Z","title":"React: Synergizing reasoning and acting in language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.875177Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:5277bfe2c32cec93184632e56ea18bfc471abb56f22d785c922c08388ddc29c6","observation_id":"2217a81a-ec19-47a0-a551-60ee68e0a615","resolution":{"observed_at":"2026-08-07T13:59:49.875177Z","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":"2026-08-07T13:59:54.968875Z","title":"Lan- guage agent tree search unifies reasoning, acting, and planning in language models","venue":null,"work_id":"1091a464-6a13-4748-8651-1c1f986bb52d","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.944329Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:f845ef41e2d55b284303c4722d0de81cb04886e08688da9ca7b0536d20e9012d","observation_id":"a56493c7-f9d4-4086-bf25-944e663b4417","resolution":{"observed_at":"2026-08-07T13:59:55.104309Z","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":"2026-08-07T13:59:54.722557Z","title":"Accessed: 2025-01-15","venue":null,"work_id":"ebc22747-8995-4ad3-85ce-ef286d458f46","year":2025},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:49.990348Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:03aa217184767a7d1ce563b15389a1bc0c0cc6d42649a436246c443f208ffdc8","observation_id":"97e81103-4aa4-4746-a62d-35297906ee71","resolution":{"observed_at":"2026-08-07T13:59:54.831021Z","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":"2026-08-07T13:59:54.512228Z","title":"Multiobjective tree- structured parzen estimator for computationally expensive optimization problems","venue":null,"work_id":"861f284b-ec78-40f8-b9e6-2deea6b4944a","year":2020},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.059657Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:9663e86e6610c15f1f0b772e1018cac4a2ae91f01012f46a9a81e4448aade61d","observation_id":"91251426-1c5a-4eca-a962-d5b65129ce47","resolution":{"observed_at":"2026-08-07T13:59:54.593414Z","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":"2026-08-07T13:59:54.317859Z","title":"Multi- objective tree-structured parzen estimator","venue":null,"work_id":"9aa23548-3e85-407f-a0cd-63fe52d13167","year":2022},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.141373Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:99a3af828c2a030611c41e2c5f70a2c1f96e3afc7d522ae72da4de4f7c3ab0c7","observation_id":"6aee3b42-f5e3-463b-8549-e8d3b0e949aa","resolution":{"observed_at":"2026-08-07T13:59:54.406195Z","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":"2026-08-07T13:59:54.213076Z","title":null,"venue":null,"work_id":"5ba9ebbf-4663-48b1-8fae-0e0d5bf69a7b","year":null},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.175227Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:e1ccdffd66fe29bd237788db9494f3f0cbc65253997994a4bc63dac8367b0d07","observation_id":"ad74e343-79c4-40bd-af37-3d40bf797b7a","resolution":{"observed_at":"2026-08-07T13:59:54.258538Z","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":"2026-08-07T13:59:54.089250Z","title":"Algorithms for hyper-parameter optimization","venue":null,"work_id":"6fdf1dbb-72f8-4d84-9db6-0a0f1dc320f7","year":2011},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.209214Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:45630847663799dd902f1bf618c7e8b0ef523a5f1a353de2d24105f195a644c7","observation_id":"3e987d18-4e7b-4ffa-a73c-8bae333bd812","resolution":{"observed_at":"2026-08-07T13:59:54.132970Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:50.266917Z","title":"Optuna: A next-generation hyperparameter optimization framework, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.266917Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:0685b38b1e96c83ab8cdcf91bbd84b48bf895c470f68f4c419a97a5844fe1976","observation_id":"00a448a3-dc73-48fb-a77c-e0ea02efae7e","resolution":{"observed_at":"2026-08-07T13:59:50.266917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.09600","last_updated":"2018-09-25T17:28:20Z","snapshot_observed_at":"2026-08-09T10:11:58.541007Z","submitted_at":"2018-09-25T17:28:20Z","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.09600","snapshot_observed_at":"2026-08-07T13:59:50.314921Z","title":"Hotpotqa: A dataset for diverse, explainable multi-hop question answering","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.314921Z"},"links":{"cited_paper":"/paper/1809.09600","citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:93d17a2a4379abad87151e6edf1701eb2bb64199514ab9c9459281c2dd4f0d55","observation_id":"28e688df-b0c5-4724-b108-72bdc7d8111f","resolution":{"observed_at":"2026-08-07T13:59:50.314921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11944","last_updated":"2023-11-20T17:28:02Z","snapshot_observed_at":"2026-07-06T16:50:06.095609Z","submitted_at":"2023-11-20T17:28:02Z","title":"FinanceBench: A New Benchmark for Financial Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.11944","snapshot_observed_at":"2026-08-07T13:59:50.372722Z","title":"Financebench: A new benchmark for financial question answering","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.372722Z"},"links":{"cited_paper":"/paper/2311.11944","citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:1c7541a878f211f9b630750513b9a2ff8689227411054dd8d454965fb0051b5d","observation_id":"ca7bb70a-200a-4478-96cb-eaac61b5ae88","resolution":{"observed_at":"2026-08-07T13:59:50.372722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-03T17:59:39.795742Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-07T13:59:50.459606Z","title":"Crag – comprehensive rag benchmark","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.459606Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:573af381db7adbb0eb072ed8d5affbe98698bc0ceff534e1a5bf3d0564272031","observation_id":"d5294252-475f-471f-8dac-589823b062df","resolution":{"observed_at":"2026-08-07T13:59:50.459606Z","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":"2026-08-07T13:59:50.545010Z","title":"∞bench: Extending long context evaluation beyond 100k tokens, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.545010Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:1d74d71b73d11865183e8b6cbcd0e822bb7c092bd98bf71bcca7088c1929fbf0","observation_id":"1721fc1f-a333-4d96-a9ee-8a0a6a56c4ee","resolution":{"observed_at":"2026-08-07T13:59:50.545010Z","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":"2026-08-07T13:59:53.943591Z","title":"Aryn — document processing for etl, rag, and analytics powered by ai","venue":null,"work_id":"e4b18504-af1c-4417-97e7-7d4ba296e490","year":null},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.618569Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:0aaef8eb6f22fe1d1bfb770de1905136163df489bb70a641b85345f2a5449111","observation_id":"12693d95-fa50-4bcc-8258-5ba29d973003","resolution":{"observed_at":"2026-08-07T13:59:54.024845Z","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":"2026-08-07T13:59:53.802127Z","title":"html2text: Convert html into markdown-formatted text, 2004","venue":null,"work_id":"2d19835d-879b-4450-9e1e-17bb3b886a88","year":2004},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.671408Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:522742bae870fd78052bce8194786ac893bdee56d8b70085cbd1116da06dc6f7","observation_id":"448b924c-e001-45be-a8b5-14ea939e6e49","resolution":{"observed_at":"2026-08-07T13:59:53.865062Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:50.741025Z","title":"Judging llm-as-a-judge with mt-bench and chatbot arena","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.741025Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:3ca2cdd1d7a2f3a06f82951c46c0c05be2c43c24c7444a5582573b54bce9c854","observation_id":"c16de0d0-66f9-4e78-adda-60b8a77aa823","resolution":{"observed_at":"2026-08-07T13:59:50.741025Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.13076","last_updated":"2024-04-15T16:49:59Z","snapshot_observed_at":"2026-07-06T18:02:53.240463Z","submitted_at":"2024-04-15T16:49:59Z","title":"LLM Evaluators Recognize and Favor Their Own Generations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.13076","snapshot_observed_at":"2026-08-07T13:59:50.789445Z","title":"Llm evaluators recognize and favor their own generations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.789445Z"},"links":{"cited_paper":"/paper/2404.13076","citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:9120be82b8d1e13c0af7e991af407e1dfd0fed2820153ab6bd3ed1df26895110","observation_id":"ff79056f-6f10-4e40-8146-140ca201ef0a","resolution":{"observed_at":"2026-08-07T13:59:50.789445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02736","last_updated":"2024-10-04T03:57:47Z","snapshot_observed_at":"2026-08-01T08:21:19.528254Z","submitted_at":"2024-10-03T17:53:30Z","title":"Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02736","snapshot_observed_at":"2026-08-07T13:59:50.841347Z","title":"Justice or prejudice? quantifying biases in llm-as-a-judge","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.841347Z"},"links":{"cited_paper":"/paper/2410.02736","citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:0e58b0a74a04df6e42372f5d9f78a20abb22d05c21c5d1bef3f68378eda75857","observation_id":"46b92dbc-1365-4c5d-846f-400e1640dc75","resolution":{"observed_at":"2026-08-07T13:59:50.841347Z","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":"2026-08-07T13:59:53.644788Z","title":"Amazon q","venue":null,"work_id":"d3573e1a-3676-4824-b3e1-873fd46abcd4","year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.898172Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:acbfdb944e358985cc003ec32f230b717a95ff4fcc46009697dc4b47e8962c7d","observation_id":"b6721535-4bc9-4db3-9ba6-2d09defbde38","resolution":{"observed_at":"2026-08-07T13:59:53.701693Z","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":"2026-08-07T13:59:53.528154Z","title":"Azure OpenAI Assistants (Preview), 2025","venue":null,"work_id":"aea404cd-59db-4846-94b7-8799e3fd9ea8","year":2025},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.979244Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:c2126eae4ddc64baab46c29fcdb40b3c86011d60b4108045c99f0d0cbccb1a7a","observation_id":"15e9764d-f146-4c7d-b592-e022e7145da4","resolution":{"observed_at":"2026-08-07T13:59:53.580386Z","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":"2026-08-07T13:59:53.425744Z","title":"Magentic-one: A generalist multi-agent system for solving complex tasks","venue":null,"work_id":"99ea61c9-b88e-47b1-bea3-089ea7d69adc","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.042951Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:05a59ac626be3eb02a637f61c561cf7de4026a158fbd48bc8bbf54007e2dd972","observation_id":"596146e3-9046-4cc6-9b86-e2b98df65eae","resolution":{"observed_at":"2026-08-07T13:59:53.467208Z","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":"2026-08-07T13:59:53.205749Z","title":"Adaptive in-conversation team building for language model agents, 2024","venue":null,"work_id":"34f49be0-2d25-4a8b-b5f2-bed6613db359","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.084006Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:fb28ecffe6d9c5a53d0e6a3295653faaca068978ef79fac88fbdc571f0a8b9dc","observation_id":"94061d7c-a202-4e52-952c-f70f8a740dd3","resolution":{"observed_at":"2026-08-07T13:59:53.333079Z","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":"2026-08-07T13:59:52.982424Z","title":"Lightweight reranking for language model generations, 2024","venue":null,"work_id":"0964dc12-4e09-4d91-9380-8b555dde4d15","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.135761Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:329dced463449fe0f162ea8defa38913be7f6f5379e4e07e51a33116cba065ce","observation_id":"c6235957-0c73-4cfd-b503-4032006485c0","resolution":{"observed_at":"2026-08-07T13:59:53.073213Z","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":"2026-08-07T13:59:52.818867Z","title":"Zero-shot listwise document reranking with a large language model, 2023","venue":null,"work_id":"512d330d-6129-4470-9c8a-28697d9002b9","year":2023},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.195166Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:fe22efb8fbc06c4217661c42b366ee8d6722a083a670c0384e5be04829b02171","observation_id":"bbfc7b59-3387-4674-b8d6-9b85ce9885a6","resolution":{"observed_at":"2026-08-07T13:59:52.915752Z","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":"2026-08-07T13:59:52.620979Z","title":"Chain-of-thought prompting elicits reasoning in large language models","venue":null,"work_id":"3327d29d-26b9-461c-87f6-c33993582891","year":2022},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.270919Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:5dad88429100e25df59565d90e2820a24de6f5967fa93565f6cfbd6ec3720c5c","observation_id":"2f61b0c0-e42e-43e8-b810-3b9314655211","resolution":{"observed_at":"2026-08-07T13:59:52.677285Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:51.324885Z","title":"Rethinking the role of demonstrations: What makes in-context learning work?, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.324885Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:450594e52e102588dc458e2ba3a6c87ec6c7ca5505d0df7f7c096cb39b1a24c2","observation_id":"930b4fc3-6216-4276-a632-e92050030919","resolution":{"observed_at":"2026-08-07T13:59:51.324885Z","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":"2026-08-07T13:59:51.397058Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.397058Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:c747852911fac69dcc97d5bac93b31c5e3d5d1cef77aa831cef21226bde67c65","observation_id":"406c71fa-6fa8-498d-99db-9cd6408455bb","resolution":{"observed_at":"2026-08-07T13:59:51.397058Z","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":"2026-08-07T13:59:52.408637Z","title":"Jordan, and Ion Stoica","venue":null,"work_id":"451b3ab5-3a51-4d20-83ea-4c0e52d9f886","year":2018},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.468645Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:f0d4cbcaa52bf881194698247b4cb621b9bcec78359c214c43b5189458ea6b39","observation_id":"da68f8a8-23c9-483d-84ad-28bde30f9037","resolution":{"observed_at":"2026-08-07T13:59:52.490123Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:51.543459Z","title":"Gonzalez, and Ion Stoica","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.543459Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:4a07161011cdd3587ec0306cf7d442f610eb8f82a21cea142c6c7102c2c3f060","observation_id":"258e8830-ca50-4f66-b451-8a593f92887e","resolution":{"observed_at":"2026-08-07T13:59:51.543459Z","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":"2026-08-07T13:59:52.261192Z","title":"https://github.com/onnx/onnx/ blob/main/docs/IR.md, 2024","venue":null,"work_id":"7dfb4e93-4d48-4b93-8fee-66c1eaa81460","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.597969Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:b6b5f40b394ce1f6b7fd5018f0a29d6db5316bba8da6e5b22eb2d48513f1a575","observation_id":"e815652e-a253-4ccd-80d2-26debbc28fec","resolution":{"observed_at":"2026-08-07T13:59:52.328359Z","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":"2026-08-07T13:59:52.155115Z","title":"Bilevel programming for hyperparameter optimization and meta-learning","venue":null,"work_id":"1e3a247a-a7bf-4cf9-a056-dadbbadbc535","year":2018},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.650619Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:588d81fb41b7493d91f34a0fffa71f32fe85d79c2052e91eb2499d380c6702cd","observation_id":"91fd3a3a-1ac6-4905-8d0b-b9c789244a62","resolution":{"observed_at":"2026-08-07T13:59:52.215222Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:59:51.711791Z","title":"Model-agnostic meta-learning for fast adaptation of deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.711791Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:71c934cc62d1a5002a2fc32e2fce4071dcc6e59bf816bc8502ffd149c0ac4c13","observation_id":"feca5a4d-19d0-4e5c-947c-f5c24b698e44","resolution":{"observed_at":"2026-08-07T13:59:51.711791Z","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":"2026-08-07T13:59:52.043193Z","title":"Meta comprehensive rag benchmark - kdd cup 2024","venue":null,"work_id":"a2a9b3ea-85f9-4c75-bcf0-f3ef7341e8bc","year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.760331Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:c152e598c5ab622ad80d5ce5020a1cdf392c7a8d3f34b7554465eece63f8b34e","observation_id":"14b3f040-1246-4968-8687-46b2c65a168e","resolution":{"observed_at":"2026-08-07T13:59:52.087428Z","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":"2026-08-07T13:59:51.959353Z","title":"distractor","venue":null,"work_id":"6340f17e-61b8-4477-a267-c5663cb31fc5","year":2025},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:51.806810Z"},"links":{"citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:d3aa3a346ff35553825e10f63a2eee6a9aa5028dc3ca4ab09ab18f1f0017b30a","observation_id":"d7beb382-7796-432b-bc5a-5fe44ba1b40f","resolution":{"observed_at":"2026-08-07T13:59:51.995250Z","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"}}],"paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T13:53:32.765940Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI"},"reference_resolution":{"displayed":76,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":52},"total_outbound_references":76},"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 76 of 76 outbound references and 2 inbound Pith citation observations for arXiv:2505.20266."}