{"as_of":"2026-08-04T03:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9abeb694925b0c3f5ed02c07ed3f805b94e54c003a140651fed3ec14c5757598","coverage":[{"denominator":13,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":13,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T18:32:37.703624Z","state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-03T06:30:56.289259+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T01:03:24.382077Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.06753","snapshot_observed_at":"2026-08-01T01:03:24.382077Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.25956","last_updated":"2026-07-28T16:41:54Z","snapshot_observed_at":"2026-08-03T06:19:48.731574Z","submitted_at":"2026-07-28T16:41:54Z","title":"Large Language Model for Operations Research Formulation Selection in Multi-Warehouse Inventory Allocation","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-01T01:03:24.382077Z"},"links":{"cited_paper":"/paper/2604.06753","citing_paper":"/paper/2607.25956"},"observation_digest":"sha256:39af0b9cfaa193928ad7b43236fcec994d9a1fa0b301f9281ea2f311858c1174","observation_id":"d94cfa5a-10d9-4a6e-9850-db91ea62abc6","resolution":{"observed_at":"2026-08-01T01:03:24.382077Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2604.06753/citation-record","integrity":"/paper/2604.06753/integrity","json":"/paper/2604.06753/citation-record.json","paper":"/paper/2604.06753"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.05176","last_updated":"2023-05-09T05:11:02Z","snapshot_observed_at":"2026-07-31T18:33:34.529799Z","submitted_at":"2023-05-09T05:11:02Z","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","version":1},"cited_work":{"arxiv_id":"2305.05176","doi":"10.48550/arxiv.2305.05176","metadata_source":"pith","pith_arxiv_id":"2305.05176","snapshot_observed_at":"2026-07-10T20:57:34.659174Z","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","venue":"cs.LG","work_id":"5c567414-35de-4373-ae7a-1790da594e8d","year":2023},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2305.05176","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:76f6e8f553f984d20095925bc70a774eb0e75d3f24052ca40ec41b7c1535095f","observation_id":"9d78e302-10f7-450c-83a7-45f97d8f3bcd","resolution":{"observed_at":"2026-05-11T19:56:45.568475Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-07-14T18:20:20.871342+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T18:20:20.871342+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.11477","last_updated":"2023-09-27T07:29:44Z","snapshot_observed_at":"2026-08-01T15:58:01.346044Z","submitted_at":"2023-04-22T20:34:03Z","title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","version":3},"cited_work":{"arxiv_id":"2304.11477","doi":"10.48550/arxiv.2304.11477","metadata_source":"pith","pith_arxiv_id":"2304.11477","snapshot_observed_at":"2026-07-11T00:27:51.551234Z","title":"LLM+P: Empowering Large Language Models with Optimal Planning Proficiency","venue":"cs.AI","work_id":"7226ffd7-2787-4b30-823a-785e230e85d1","year":2023},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2304.11477","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:35847f05a1cf562fec8b0d6570819a80c2b7171b02a8c9190a40e259b7b2b9bb","observation_id":"94bdf6e6-6c67-4ad3-8799-8037e75b6d84","resolution":{"observed_at":"2026-05-14T18:36:18.754973Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18665","last_updated":"2025-02-23T08:50:33Z","snapshot_observed_at":"2026-07-30T15:06:18.011623Z","submitted_at":"2024-06-26T18:10:22Z","title":"RouteLLM: Learning to Route LLMs with Preference Data","version":4},"cited_work":{"arxiv_id":"2406.18665","doi":"10.48550/arxiv.2406.18665","metadata_source":"pith","pith_arxiv_id":"2406.18665","snapshot_observed_at":"2026-07-10T20:57:34.931879Z","title":"RouteLLM: Learning to Route LLMs with Preference Data","venue":"cs.LG","work_id":"f6b91d8a-ce78-4b5e-9dae-6dd8a22cc087","year":2024},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2406.18665","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:a73c5e9103ae107acaaecb787742724b84a6d2a0b96fba95a432bbe563dd913d","observation_id":"711a35eb-0769-43a4-8015-752aa2e5b7bd","resolution":{"observed_at":"2026-05-11T23:27:40.993552Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-07-14T18:20:21.122549+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T18:20:21.122549+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.14249","last_updated":"2026-02-20T04:23:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-24T05:27:46Z","title":"Humanity's Last Exam","version":10},"cited_work":{"arxiv_id":"2501.14249","doi":"10.1038/s41586-025-09962-4","metadata_source":"pith","pith_arxiv_id":"2501.14249","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Humanity's Last Exam","venue":"cs.LG","work_id":"59ea00d4-16a8-45e1-aafc-290a6f91d9f4","year":2025},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2501.14249","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:0e86cf1a5c7b5769ae53c8dd2de11007354ee230b6ef3eacc3c4511502a6b418","observation_id":"d786e55b-2582-459c-96ee-0842414b32a8","resolution":{"observed_at":"2026-05-11T00:25:50.918265Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T22:08:32.844211+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T22:08:32.844211+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-03T22:08:32.844211+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":"2505.09388","doi":"10.1016/j.aiopen.2022.12","metadata_source":"pith","pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Qwen3 Technical Report","venue":"cs.CL","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","year":2025},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:837ee86eb524d44fcb359917103ed5785cdeecbe44008ba048e57c9ae3ef4e2c","observation_id":"daf75198-97b0-422f-8079-db9f3f963813","resolution":{"observed_at":"2026-05-11T00:25:50.892186Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15789","last_updated":"2023-09-27T17:08:40Z","snapshot_observed_at":"2026-07-06T16:24:30.545494Z","submitted_at":"2023-09-27T17:08:40Z","title":"Large Language Model Routing with Benchmark Datasets","version":1},"cited_work":{"arxiv_id":"2309.15789","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.15789","snapshot_observed_at":"2026-07-11T02:27:47.646520Z","title":"Large language model routing with benchmark datasets","venue":"cs.CL","work_id":"56d9bd9c-33d3-4d15-80bf-a522f51610b7","year":2023},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2309.15789","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:248b494882311859078582e9e22c3d13f1f60bf6e50912d78f1f25000833108b","observation_id":"99cffbfd-f1de-4523-82fe-5a4a72f9132f","resolution":{"observed_at":"2026-05-11T00:25:50.940194Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03314","last_updated":"2024-08-06T17:35:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-06T17:35:05Z","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","version":1},"cited_work":{"arxiv_id":"2408.03314","doi":"10.18653/v1/2025.acl-long.1486","metadata_source":"pith","pith_arxiv_id":"2408.03314","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","venue":"cs.LG","work_id":"a8d50b24-bdf5-46ed-bc4f-2927dfd81f1d","year":2024},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2408.03314","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:cc805ab4deeb2fc1453802662b6d0c428f7e9dceef5f5f42959d027c4620aa25","observation_id":"93f6a832-6885-4366-9d2a-769a21ac5223","resolution":{"observed_at":"2026-05-11T00:25:50.960902Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.04091","last_updated":"2023-05-26T07:06:48Z","snapshot_observed_at":"2026-07-06T15:24:07.662207Z","submitted_at":"2023-05-06T16:34:37Z","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","version":3},"cited_work":{"arxiv_id":"2305.04091","doi":"10.48550/arxiv.2305.04091","metadata_source":"pith","pith_arxiv_id":"2305.04091","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","venue":"cs.CL","work_id":"077c8bd4-de74-49bd-be87-4cb72bac1b73","year":2023},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2305.04091","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:740ff9c57328f3db61405e4d4d2a319cbfc5ea7da2e3358c97f74a7aca957644","observation_id":"c20d82ca-fa79-4c1a-9467-5ea7d1429a93","resolution":{"observed_at":"2026-05-16T08:43:46.984626Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11171","last_updated":"2023-03-07T17:57:37Z","snapshot_observed_at":"2026-07-06T12:50:22.773056Z","submitted_at":"2022-03-21T17:48:52Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","version":4},"cited_work":{"arxiv_id":"2203.11171","doi":"10.1101/2025.04.03.646459","metadata_source":"pith","pith_arxiv_id":"2203.11171","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","venue":"cs.CL","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","year":2022},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2203.11171","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:c7d58c5efacb2154347a07f4b9e8cc955913d6d4027d7835dbd502f0074b4eef","observation_id":"5d785746-e02a-4274-afe1-2b2244caff6f","resolution":{"observed_at":"2026-05-11T00:25:50.970304Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-05-21T18:52:42.88633+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T18:52:42.88633+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14192","last_updated":"2026-07-03T11:26:58Z","snapshot_observed_at":"2026-08-03T09:21:30.130466Z","submitted_at":"2026-01-20T17:51:56Z","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","version":2},"cited_work":{"arxiv_id":"2601.14192","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2601.14192","snapshot_observed_at":"2026-07-07T02:16:02.482997Z","title":"arXiv preprint arXiv:2601.14192 , year=","venue":null,"work_id":"31754071-82a9-46af-825a-b4da22f4f634","year":2026},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2601.14192","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:6644c48b4e10ed5f7e51b22772370d9bb4653194d3dc33917ea04e358c1ff631","observation_id":"f0925a76-9055-49d1-981b-0899a721e394","resolution":{"observed_at":"2026-07-07T02:16:02.482997Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.12045","last_updated":"2024-06-17T19:33:08Z","snapshot_observed_at":"2026-08-02T22:19:29.043854Z","submitted_at":"2024-06-17T19:33:08Z","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","version":1},"cited_work":{"arxiv_id":"2406.12045","doi":"10.48550/arxiv.2406.12045","metadata_source":"pith","pith_arxiv_id":"2406.12045","snapshot_observed_at":"2026-07-11T01:37:42.734447Z","title":"$\\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains","venue":"cs.AI","work_id":"6a8d8dc4-0cc0-4052-8109-abbcdcd4a962","year":2024},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"cited_paper":"/paper/2406.12045","citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:93102c5d42e301eebad7411e010b7f821165246175a87057cfc2647819b441fd","observation_id":"feb0c6b9-5f71-4f44-9d6b-6f54109872e1","resolution":{"observed_at":"2026-05-11T03:19:00.987380Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-07-14T18:20:21.86453+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T18:20:21.86453+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-03T06:30:50.922721+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":"2026-06-05T21:23:00.469572Z","title":"SATISFACTORY","venue":null,"work_id":"7423cfe5-8832-4cc9-809d-409c1cb7fefd","year":2000},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:6f6ad957c954f10ce673ad7c9eb2710ab8dd2ce04b217a605863837a1a8eb486","observation_id":"664b6dff-9914-4b05-8cdf-7d80f4369443","resolution":{"observed_at":"2026-05-16T18:33:16.127920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+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":"2026-06-05T21:23:00.469572Z","title":"India” based on parametric knowledge. Most strikingly, Reflection made 10 tool calls andstillanswered “India","venue":null,"work_id":"f29b6087-86cf-4796-b90a-1e844ed83a8c","year":2023},"citing_paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T18:32:37.703624Z"},"links":{"citing_paper":"/paper/2604.06753"},"observation_digest":"sha256:a5b295e6f5f3f888adfed813cc5be86dc20907ee816f4aa68ca5a8be3185f586","observation_id":"1cf98632-5170-4d5f-9d66-8fed0637c237","resolution":{"observed_at":"2026-05-16T18:33:16.125347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.06753","last_updated":"2026-04-08T07:20:23Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-02T06:33:22.851554Z","submitted_at":"2026-04-08T07:20:23Z","title":"Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents"},"reference_resolution":{"displayed":13,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":0,"verified_exact":10,"verified_fuzzy":2},"total_outbound_references":13},"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":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 1 inbound Pith citation observation for arXiv:2604.06753."}