{"as_of":"2026-08-17T16:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d292999a0e18953a168a7cdfcd391f67a14dd1115f271cf415afaf67a00d76b5","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T14:53:25.764212Z","state":"measured"},{"denominator":57,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":57,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":7,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":7,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:21:21.635257Z","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":"2026-07-03T08:07:45.281283Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01618","snapshot_observed_at":"2026-08-16T12:21:21.635257Z","title":"(Cited on p","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.13139","last_updated":"2025-04-18T18:45:25Z","snapshot_observed_at":"2026-08-17T12:02:03.632069Z","submitted_at":"2025-04-17T17:49:40Z","title":"Syntactic and Semantic Control of Large Language Models via Sequential Monte Carlo","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T12:21:21.635257Z"},"links":{"cited_paper":"/paper/2502.01618","citing_paper":"/paper/2504.13139"},"observation_digest":"sha256:0e1cec7ac315e89c5ecadd01b34e6791504f85dc1cfdd1bae09b865021c32b60","observation_id":"a83d1d9b-98fd-429e-8173-cf0deb8bcb9d","resolution":{"observed_at":"2026-08-16T12:21:21.635257Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01618","snapshot_observed_at":"2026-08-16T00:05:48.297295Z","title":"A probabilistic inference approach to inference-time scaling of llms using particle-based monte carlo methods,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.03156","last_updated":"2025-05-06T04:03:11Z","snapshot_observed_at":"2026-08-17T12:02:03.980930Z","submitted_at":"2025-05-06T04:03:11Z","title":"Soft Best-of-n Sampling for Model Alignment","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T00:05:48.297295Z"},"links":{"cited_paper":"/paper/2502.01618","citing_paper":"/paper/2505.03156"},"observation_digest":"sha256:51e5ec26900d01985709a68c9197bd9f200965f646ada9ae7c84db9e2d3842aa","observation_id":"c75a4f7a-0f72-48d6-84ff-dbe03275e144","resolution":{"observed_at":"2026-08-16T00:05:48.297295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"cited_work":{"arxiv_id":"2502.01618","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01618","snapshot_observed_at":"2026-07-03T08:07:45.281283Z","title":"A probabilistic inference approach to inference-time scaling of llms using particle-based monte carlo methods","venue":null,"work_id":"6d2b732c-6772-403a-b73b-538c2e050588","year":2025},"citing_paper":{"arxiv_id":"2505.11737","last_updated":"2026-04-11T18:08:02Z","snapshot_observed_at":"2026-08-17T03:22:33.652659Z","submitted_at":"2025-05-16T22:47:32Z","title":"TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-22T13:58:07.913104Z"},"links":{"cited_paper":"/paper/2502.01618","citing_paper":"/paper/2505.11737"},"observation_digest":"sha256:40a163e96a97786393b5246a87e15caafe9683b6b6417152cb52de339b36755d","observation_id":"da84079e-e322-4881-b5e9-fcb073f7d014","resolution":{"observed_at":"2026-05-22T14:01:38.371687Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"cited_work":{"arxiv_id":"2502.01618","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01618","snapshot_observed_at":"2026-07-03T08:07:45.281283Z","title":"A probabilistic inference approach to inference-time scaling of llms using particle-based monte carlo methods","venue":null,"work_id":"6d2b732c-6772-403a-b73b-538c2e050588","year":2025},"citing_paper":{"arxiv_id":"2507.08390","last_updated":"2026-08-06T22:52:14Z","snapshot_observed_at":"2026-08-13T22:18:55.748799Z","submitted_at":"2025-07-11T08:00:47Z","title":"Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement","version":4},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-05-19T05:02:15.241418Z"},"links":{"cited_paper":"/paper/2502.01618","citing_paper":"/paper/2507.08390"},"observation_digest":"sha256:41691514f79126b8b2d854e36943b9757b89f6934d8e7b493ec42fac7b34262b","observation_id":"e8aaa572-1324-4352-99f9-19c56d0c3dbc","resolution":{"observed_at":"2026-05-19T05:02:58.822888Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"cited_work":{"arxiv_id":"2502.01618","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01618","snapshot_observed_at":"2026-07-03T08:07:45.281283Z","title":"A probabilistic inference approach to inference-time scaling of llms using particle-based monte carlo methods","venue":null,"work_id":"6d2b732c-6772-403a-b73b-538c2e050588","year":2025},"citing_paper":{"arxiv_id":"2510.14703","last_updated":"2026-04-28T18:17:43Z","snapshot_observed_at":"2026-08-13T13:25:07.876055Z","submitted_at":"2025-10-16T14:06:03Z","title":"ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-18T06:30:39.858246Z"},"links":{"cited_paper":"/paper/2502.01618","citing_paper":"/paper/2510.14703"},"observation_digest":"sha256:87b6da55801538a075ae3f622b7a317432e3b1682ea55088a33e9db2314d4716","observation_id":"1717e218-1d08-4c5f-84ab-a7999bc19126","resolution":{"observed_at":"2026-05-18T06:30:59.602288Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"cited_work":{"arxiv_id":"2502.01618","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01618","snapshot_observed_at":"2026-07-03T08:07:45.281283Z","title":"A probabilistic inference approach to inference-time scaling of llms using particle-based monte carlo methods","venue":null,"work_id":"6d2b732c-6772-403a-b73b-538c2e050588","year":2025},"citing_paper":{"arxiv_id":"2511.22277","last_updated":"2026-04-24T08:52:17Z","snapshot_observed_at":"2026-08-11T02:15:49.098646Z","submitted_at":"2025-11-27T09:59:39Z","title":"TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-17T04:19:18.805697Z"},"links":{"cited_paper":"/paper/2502.01618","citing_paper":"/paper/2511.22277"},"observation_digest":"sha256:0f36f7452d1baa9b4bb986fa064bf15b34d6a3b0db4d381b72301916e4fac54e","observation_id":"6738b39e-23a9-4f27-a64f-510004607c15","resolution":{"observed_at":"2026-05-17T04:21:30.832746Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"cited_work":{"arxiv_id":"2502.01618","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01618","snapshot_observed_at":"2026-07-03T08:07:45.281283Z","title":"A probabilistic inference approach to inference-time scaling of llms using particle-based monte carlo methods","venue":null,"work_id":"6d2b732c-6772-403a-b73b-538c2e050588","year":2025},"citing_paper":{"arxiv_id":"2606.11437","last_updated":"2026-06-09T20:48:48Z","snapshot_observed_at":"2026-08-13T04:27:41.134413Z","submitted_at":"2026-06-09T20:48:48Z","title":"The Power of Test-Time Training for Approximate Sampling","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-27T11:07:47.543592Z"},"links":{"cited_paper":"/paper/2502.01618","citing_paper":"/paper/2606.11437"},"observation_digest":"sha256:053c8c6a9fb6971ae5affaf7b1e7912d6336690875cd3c79d1ac6c590e1f8735","observation_id":"320fd871-47a7-4018-ab0e-1d13044146ac","resolution":{"observed_at":"2026-07-03T08:07:45.282752Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.01618/citation-record","integrity":"/paper/2502.01618/integrity","json":"/paper/2502.01618/citation-record.json","paper":"/paper/2502.01618"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:53:27.450819Z","title":"Aimo validation aime dataset","venue":null,"work_id":"bb7a6b49-a32d-49d0-a629-e2508307abeb","year":2023},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:24.778692Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:02ffb1e55f75cdc8673582d79de595ade9d78626b27c10773eaea2d98cb6a2ec","observation_id":"6cf1ad45-c8e6-4f75-9a4d-41512460d493","resolution":{"observed_at":"2026-08-09T14:53:27.454062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:27.439129Z","title":"Particle Markov Chain Monte Carlo Methods","venue":null,"work_id":"303017bf-ba58-410a-83f0-2a76c5df89ce","year":2010},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:24.859006Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:fed67e2bf318d9e3c68785ef2da545173bfa44f82c306450a0a54652041fea61","observation_id":"31548382-63a9-4055-9e5a-05157d634b19","resolution":{"observed_at":"2026-08-09T14:53:27.444718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:24.894041Z","title":"Scaling test-time compute with open models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:24.894041Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:1f95028ed2a428ae242d577df829a14073b09edfc05a957dbe83ab7fb89f09f6","observation_id":"246aa963-c717-4fe3-8d79-403f31695bd5","resolution":{"observed_at":"2026-08-09T14:53:24.894041Z","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":"2026-08-09T14:53:27.422790Z","title":"Le, Christopher Ré, and Azalia Mirhoseini","venue":null,"work_id":"db11fb96-5f4c-4bce-84f8-8d40e7c7ca6f","year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:24.955566Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:8ab35162085d42d449245c13d14bf6ec4b30490269116d1e02a1d7e0591acf78","observation_id":"738b7722-00aa-4a9c-9e4a-deaa13c7eb61","resolution":{"observed_at":"2026-08-09T14:53:27.426529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:27.411173Z","title":"Boltzmann exploration done right","venue":null,"work_id":"ef7cf954-6261-43df-8c81-4384ca46e397","year":2017},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.012716Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:2e1e613ff85363f0c0f4881eb4fcda15d6fd5b121cd5731cfced23778559b17a","observation_id":"aaa25576-97af-4477-9444-8859e40d209f","resolution":{"observed_at":"2026-08-09T14:53:27.415628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:27.331644Z","title":"Process reinforcement through implicit rewards, 2025","venue":null,"work_id":"5fbe8f13-b32f-49ea-8fc4-a1cd24827fc6","year":2025},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.072670Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:81dafb6d7a20b747dc4d98ad046c09758eee8e4149b4415b1768dee08309d83b","observation_id":"25d444e2-e10a-4664-a7d4-6efc69916b98","resolution":{"observed_at":"2026-08-09T14:53:27.368696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T14:53:26.068760Z","title":"Sequential Monte Carlo Methods for Dynamic Sys- tems: Journal of the American Statistical Association: V ol 93, No 443","venue":null,"work_id":"c47328e1-1ece-4fc2-b2a6-b042271fa557","year":1998},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.146674Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:fcc707b16eb84953466db180c642364911b03065e888e5ff16352bff5dd2bb33","observation_id":"3dc6ba93-63eb-41d7-b6b2-bbdc0970c850","resolution":{"observed_at":"2026-08-09T14:53:26.115156Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:27.259017Z","title":"Step-by-step reasoning for math problems via twisted sequential monte carlo, 2024","venue":null,"work_id":"88118d47-973e-4b37-b895-98741352a4df","year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.172198Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:d2e6ca018509465f1ea6e77e2a37d1fad6526ceed65f33c759041395d5819413","observation_id":"2ae85271-ac8a-4252-a0a1-089ab8e0ad40","resolution":{"observed_at":"2026-08-09T14:53:27.297833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:27.146490Z","title":"Tenenbaum, Vikash K","venue":null,"work_id":"5914544d-58fe-4cf8-beb9-df1eafb5e6f6","year":2025},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.207792Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:46ec86271e3ec3fc64b87bd0d590d73e37fc139d12144f58e4a918c1d4c77572","observation_id":"8352d0c6-6a12-4ae5-b727-3ee85f24fabf","resolution":{"observed_at":"2026-08-09T14:53:27.206865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:27.083934Z","title":null,"venue":null,"work_id":"c3eb7708-6b6e-4694-a000-9179faba4bd0","year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.211702Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:1edbc8d9f1bb44f69c122091d2417576cf91ae304fed0001cd0d8af4f0cff4ed","observation_id":"65ea630c-6b11-4702-9926-65cae2a7b741","resolution":{"observed_at":"2026-08-09T14:53:27.109557Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:27.072895Z","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking, January 2025","venue":null,"work_id":"17bc14d2-9477-4dcf-87bf-4be17dbcc8b0","year":2025},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.215748Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:2b384d2464b2caa755046ad4d98a86d32a61e3a5e8fe8a0edcd1a051a079c039","observation_id":"a0e3e554-aae0-43ff-834a-9263594f981b","resolution":{"observed_at":"2026-08-09T14:53:27.076826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:25.219901Z","title":"Financebench: A new benchmark for financial question answering, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.219901Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:34cc8705d738542516a1f77fbddbc8405bb51d93e1b928ba05bdb088ad014a2d","observation_id":"1e3684b5-b334-44c3-9459-1e311ad348b8","resolution":{"observed_at":"2026-08-09T14:53:25.219901Z","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":"2026-08-09T14:53:25.223922Z","title":"Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.223922Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:bb4c03efa5be4081f15d1d47a8840bee8fd53a8bde0231b3f5f1e399e1c7cd3c","observation_id":"9289fb3f-fbc2-4551-a0e3-88c33d4bc381","resolution":{"observed_at":"2026-08-09T14:53:25.223922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1402.6028","last_updated":"2014-02-25T01:34:43Z","snapshot_observed_at":"2026-08-17T00:30:50.886580Z","submitted_at":"2014-02-25T01:34:43Z","title":"Algorithms for multi-armed bandit problems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1402.6028","snapshot_observed_at":"2026-08-09T14:53:25.226837Z","title":"Algorithms for multi-armed bandit problems.arXiv preprint arXiv:1402.6028, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.226837Z"},"links":{"cited_paper":"/paper/1402.6028","citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:cce31b0060b7f4f697ee8b46be754d186107f9caea5e1bafdb9632cf49caa635","observation_id":"d9a138dd-47e2-4111-8ba3-417e072aaa83","resolution":{"observed_at":"2026-08-09T14:53:25.226837Z","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":"2026-08-09T14:53:27.049086Z","title":"Lew, Tan Zhi-Xuan, Gabriel Grand, and Vikash K","venue":null,"work_id":"0b4686df-29e9-4417-ac42-60e376948b22","year":2023},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.230986Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:a2e540e1f7a4d1aae12583d65e8a2abda5b0e17014e3ef6cf5de55297efb4d7f","observation_id":"606e6a64-7722-47e8-80d1-f5bf1745655c","resolution":{"observed_at":"2026-08-09T14:53:27.052335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:25.234912Z","title":"Let’s verify step by step, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.234912Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:bc90ce8231c6594469015c6a3cd6162dcd284a748c25bedd9d0b3a582b5624c4","observation_id":"bdffaacf-5bd5-43cf-a170-b40dc608b19e","resolution":{"observed_at":"2026-08-09T14:53:25.234912Z","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":"2026-08-09T14:53:25.238646Z","title":"Let’s Verify Step by Step, May 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.238646Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:4782d159ad3612ed625d0a096864ec938ff1cb490ebc12f8d42edac155772e63","observation_id":"acc702a1-ff5d-4630-93f7-aa71da9e1387","resolution":{"observed_at":"2026-08-09T14:53:25.238646Z","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":"2026-08-09T14:53:27.024454Z","title":"Lew, Tim Vieira, and Timothy J","venue":null,"work_id":"3528f258-83de-4024-9276-2ff7e9bd4aab","year":2025},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.242446Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:a6f7e6e782d37094bd18fa10c7e44cd044703e882537c8eb898debe2dccb1bf6","observation_id":"622441b0-2883-4203-9c45-00e1ef67015a","resolution":{"observed_at":"2026-08-09T14:53:27.028256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:25.245787Z","title":"Cambridge university press, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.245787Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:d2804e4e980a89456169fc0967c79f326b372e7e467aad8083975d74ac513361","observation_id":"026b9a96-fc8d-44a6-af85-0a85af6d56b9","resolution":{"observed_at":"2026-08-09T14:53:25.245787Z","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":"2026-08-09T14:53:27.004399Z","title":"Numglue: A suite of fundamental yet challenging mathematical reasoning tasks","venue":null,"work_id":"5e4b5844-932a-4819-b1bd-b15ad08d6d6b","year":2022},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.249517Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:d522d70b530ff976dac4e4cafac012db96272e6afd687c92bb145eb4cd9d77fb","observation_id":"aa066491-ead5-4908-bd25-4e225e989d52","resolution":{"observed_at":"2026-08-09T14:53:27.008731Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.993042Z","title":null,"venue":null,"work_id":"16b041e6-3d45-468d-8f5b-367b20de4e56","year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.253122Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:916b4bd7345635b87ddc8ee3407da471fedb0a509613f7bfe6215e989cdbee47","observation_id":"e340161a-ad1a-45e8-ada3-1d6f1a21ef7c","resolution":{"observed_at":"2026-08-09T14:53:26.996537Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.979010Z","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters, August 2024","venue":null,"work_id":"590886be-4375-4281-be9c-e10e36ff3e4e","year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.257011Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:28487f77136259f9202aaa0f420f01fd6d2282d5f58b40f10b1203e6ddb12dcf","observation_id":"56ffbf9b-fd15-4f8f-b735-a77fe4d51089","resolution":{"observed_at":"2026-08-09T14:53:26.983727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:25.260612Z","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":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.260612Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:15b54f173d19da362dacce2069cef6d5e4bb454dbed78c257daf55ecd3c2a66b","observation_id":"b73e66c0-c4be-4b47-85d1-9bb2f3abc8ea","resolution":{"observed_at":"2026-08-09T14:53:25.260612Z","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":"2026-08-09T14:53:26.957430Z","title":"Swendsen and Jian-Sheng Wang","venue":null,"work_id":"8faf45b7-ae1d-4732-a77e-5e94fa192de2","year":1986},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.274738Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:b4c7036f47f70adb851a7505db2a97ec9baa7ec17013b447312240cf316d1e4e","observation_id":"6b26fe17-168e-43e8-850f-9fafba2bdbf3","resolution":{"observed_at":"2026-08-09T14:53:26.962290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.945767Z","title":"Bayesian Filtering and Smoothing","venue":null,"work_id":"b61d0a24-002c-4696-b419-c5f28d24ea43","year":2013},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.295526Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:2ca3c9fdd9115b857a1da168520dbfcd67f28f695882487813c719996496e1f6","observation_id":"e336940b-67b1-43bc-984e-dc6cde056f3d","resolution":{"observed_at":"2026-08-09T14:53:26.949285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:25.310700Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.310700Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:80ae9bca7f278fd103d94006af1ee37da8231776d753c3f3974a475a065de4b9","observation_id":"17d09c9f-ce09-4865-8535-feb1b226f660","resolution":{"observed_at":"2026-08-09T14:53:25.310700Z","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":"2026-08-09T14:53:25.322819Z","title":"Self-consistency improves chain of thought reasoning in language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.322819Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:bcc5ab11b896d2d19d7a281d2b7529a232e504171d7a8e3f90c6bec0c0818536","observation_id":"2cad9b0b-e16d-410f-ad0d-151404d99e70","resolution":{"observed_at":"2026-08-09T14:53:25.322819Z","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":"2026-08-09T14:53:26.917295Z","title":"An implementation of generative prm","venue":null,"work_id":"6b123b54-a8d2-4124-973b-c7aa9339d8f0","year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.360631Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:777e057634fa718020cf01ca3f63e4d23f0390eef7213c01c2f3e3e3ea85d361","observation_id":"91b35a13-0549-4d60-b6ea-8b161f359b83","resolution":{"observed_at":"2026-08-09T14:53:26.924189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12122","last_updated":"2024-09-18T16:45:37Z","snapshot_observed_at":"2026-08-14T16:00:41.902820Z","submitted_at":"2024-09-18T16:45:37Z","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12122","snapshot_observed_at":"2026-08-09T14:53:25.385934Z","title":"Qwen2.5-math technical report: Toward mathematical expert model via self-improvement","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.385934Z"},"links":{"cited_paper":"/paper/2409.12122","citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:52404c4113337de90db3b6f4848c592b4f0e471c0513a2a2bdbdfe353ea82375","observation_id":"4a662bbd-a225-4110-bc17-bdeb42602853","resolution":{"observed_at":"2026-08-09T14:53:25.385934Z","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":"2026-08-09T14:53:26.894070Z","title":"Advancing llm reasoning generalists with preference trees, 2024","venue":null,"work_id":"de7431c2-575c-4eec-9216-e768c0d5a954","year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.450110Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:54ad10072969f21d6c92b6aa3d20b6cdb724f06c6febefb8035526d92dc7981c","observation_id":"610c2005-8c27-41a0-b4b4-e47cb4149636","resolution":{"observed_at":"2026-08-09T14:53:26.905452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.07301","last_updated":"2025-06-05T16:34:24Z","snapshot_observed_at":"2026-08-17T12:00:23.281116Z","submitted_at":"2025-01-13T13:10:16Z","title":"The Lessons of Developing Process Reward Models in Mathematical Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.07301","snapshot_observed_at":"2026-08-09T14:53:25.495229Z","title":"The lessons of developing process reward models in mathematical reasoning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.495229Z"},"links":{"cited_paper":"/paper/2501.07301","citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:84c7a73ac49e26a48f0b7806a7ff58ae72dfa77a499ce2a99fe92882d4a7ed68","observation_id":"779de308-875c-4c20-893a-0bdb876919a0","resolution":{"observed_at":"2026-08-09T14:53:25.495229Z","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":"2026-08-09T14:53:25.531386Z","title":"The Lessons of Developing Process Reward Models in Mathematical Reasoning, January 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.531386Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:db73ae5f004af481de94d02a0c3e506cf099d40e40affcc0e67aa76b6dad62d2","observation_id":"171beefb-a61f-4662-829e-7f01cd57d485","resolution":{"observed_at":"2026-08-09T14:53:25.531386Z","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":"2026-08-09T14:53:26.858579Z","title":"Probabilistic inference in language models via twisted sequential monte carlo, 2024","venue":null,"work_id":"cf63c5f2-6f80-488e-9d1c-23c30d472054","year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.534836Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:6a4a09cf7f34fcfce51ef5057c4f0d9ddd1ad34ec04634702820e2475dcb5645","observation_id":"c38f4df9-4fe4-47a5-a7e8-69797597ef7b","resolution":{"observed_at":"2026-08-09T14:53:26.878857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.796271Z","title":"Language agent tree search unifies reasoning acting and planning in language models, 2024","venue":null,"work_id":"c9578421-65ab-4085-8894-5713eaf37855","year":2024},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.538184Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:98c97976c47707afede99ab7802beac3e4a642eb02222cf2bac40cb84979068d","observation_id":"5186d23c-a0a2-4557-b215-1fe9ad8550b7","resolution":{"observed_at":"2026-08-09T14:53:26.830518Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.747071Z","title":"Please see the Evaluation section for our empirical results","venue":null,"work_id":"964dee41-8dba-44b3-ab93-f2a921e59bcb","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.542005Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:0df5866f0df91480508f5e8c473f90e230dd94a7ca7a6bbd22a52098b521d858","observation_id":"63c25e6e-04e6-42f9-997e-a5ea7773fb83","resolution":{"observed_at":"2026-08-09T14:53:26.769815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.706521Z","title":"Limitations","venue":null,"work_id":"16ab082b-112e-472d-8685-0b32a849ca9f","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.545602Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:52f71d3e80743955d0c10f1170fc7cb056d2ff5f43848d34b2f501b9604493c9","observation_id":"26ef4fea-0aab-43b7-bba5-0233367ac9b7","resolution":{"observed_at":"2026-08-09T14:53:26.720721Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.684729Z","title":"Guidelines: • The answer NA means that the paper does not include theoretical results","venue":null,"work_id":"b9e148c8-0a8d-4e12-8265-98627e358e92","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.549274Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:e8949510d20680e92ca9e60bdaeee17b505e3dfac8fdf51c4777c4eebb531677","observation_id":"a81dd41c-5d79-4305-befe-4f5471bbae96","resolution":{"observed_at":"2026-08-09T14:53:26.692498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.653304Z","title":"We also provide key details into the hyperparameter selection and ablation process, which significantly helps reproducability","venue":null,"work_id":"899916bf-bdf9-44da-91a4-cfc7d4be4e3d","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.553847Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:9bfb4e59ca972547eeaa933b6b5c8edc5c8dc52dfa0ad9225baebecabd5f3a2f","observation_id":"cc0adb9e-5989-49d2-b5b3-26b0d1dd7a6e","resolution":{"observed_at":"2026-08-09T14:53:26.672372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.558621Z","title":"How- ever, we will completely open source our code upon acceptance of the paper to encourage as many people as possible to use our work","venue":null,"work_id":"7772034d-e044-47c7-99eb-4278a1fb3cd0","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.567849Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:9f6ae554533c87641b092ec4918cb3ab2dbd535d67ad36370887ef9b49ef86f1","observation_id":"c9d344c4-9d78-4e3c-85c0-198dccf8a47d","resolution":{"observed_at":"2026-08-09T14:53:26.597306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.476278Z","title":"We list exactly which models and versions we used as generator models","venue":null,"work_id":"db4532f9-1f0b-46dd-a9d5-d9aa65f1d01c","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.591566Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:efa5ec055632909a46659e64776de8ae1673083e2f00c0e381240509d8602b84","observation_id":"54d66c1e-63bc-456c-9d51-ae99c1e3f9e0","resolution":{"observed_at":"2026-08-09T14:53:26.531917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.419085Z","title":null,"venue":null,"work_id":"b3a97695-0447-4106-a992-00443080e455","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.606793Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:a390d116f72d8608b7cefe57d182c684aa654763426c3f25331ae779a10757f2","observation_id":"210b7561-11ac-4334-91f2-a82a0b429615","resolution":{"observed_at":"2026-08-09T14:53:26.443204Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.399520Z","title":null,"venue":null,"work_id":"bd59c65d-5717-4567-93d3-c68129615845","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.617660Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:65827b5e5f9b5ee4f36738bafcbf839c5d946f83bfd4acc71ea9c750cb033829","observation_id":"80e59ec3-66dc-43ac-9f3b-ac19835a6b5c","resolution":{"observed_at":"2026-08-09T14:53:26.402819Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.388274Z","title":"Our research does not have negative societal consequences, nor does it involve human subjects","venue":null,"work_id":"c03cb164-5ddf-4a89-b67f-8868225e54cb","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.629209Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:f3666481437f978f1ade56c2fb5388ffbcab6815976f36a90d6b35054ca5468d","observation_id":"34b075fe-e292-4ef8-b697-e4e0e7c166dd","resolution":{"observed_at":"2026-08-09T14:53:26.392240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.377501Z","title":"We discuss the positive impacts of inference scaling, as it opens up higher level language model performance to those who are only able to access smaller models","venue":null,"work_id":"8517c29f-3cd9-4bb3-9269-e53d865d0358","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.639563Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:3f78d7c39913c1fda9f3941daf88483b4e705fd6f11ac01ce8bdaa9c5ec54b00","observation_id":"16734161-4135-45cd-a9c2-802b9f53623c","resolution":{"observed_at":"2026-08-09T14:53:26.381240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.365758Z","title":"Instead, we only use off-the-shelf open source models, and therefore there are no possibilities of misuse","venue":null,"work_id":"56eb5d7a-f2a9-4178-a08d-bedcb9471d9a","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.652078Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:ba420b9761c088b1564d63bb131a6fa0ad8d88ac9e874bb60414878ba303eef3","observation_id":"cbf935d6-9b49-43c5-b2e3-0ce9aa5d224a","resolution":{"observed_at":"2026-08-09T14:53:26.370379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.354429Z","title":"Therefore, all creators of the original models are credited in this work","venue":null,"work_id":"98b071a5-89f3-4d9a-b557-fe13a1395ce3","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.663641Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:88264e7e406ca6b9e332d20261e5902ab8cda892b21eab5d4f2e0bbed1de1deb","observation_id":"8116b590-7649-478f-ab03-04bd613d7579","resolution":{"observed_at":"2026-08-09T14:53:26.358357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.342714Z","title":"Justification: We do not release any new assets in this paper - instead, we discuss how to enhance the performance of already existing open-sourced models","venue":null,"work_id":"83644b0f-48d1-4e82-85ce-bc61773a3c25","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.677736Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:2a3a2ca3871c2230d00be00602a683549a2cbc14b8f7a0af62e954000a791e14","observation_id":"ab6edef1-4d2e-4184-b1fa-ec78cbed50b2","resolution":{"observed_at":"2026-08-09T14:53:26.347055Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.330167Z","title":"Guidelines: 26 • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects","venue":null,"work_id":"cd03ef9c-6b79-427f-8d77-b5f1c3e55d25","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.691164Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:240005c119fecafacf4ba6c8d954a4eb4493935ce06cc7241cebfde209803c5f","observation_id":"6bb54aaf-27b9-4583-8f3f-53d788819ea2","resolution":{"observed_at":"2026-08-09T14:53:26.334857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.263067Z","title":"Justification: Our work does not include any human subjects, and we did not need IRB approvals","venue":null,"work_id":"862ceff7-92ee-46e4-b353-a136e5d613a0","year":null},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.711491Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:eef3ee3d9eb36730f89c71a32a8c892a0d045f404853a7e993276c7e5eb5850f","observation_id":"baaaed20-58e6-4731-bdcb-4dee1a803cf3","resolution":{"observed_at":"2026-08-09T14:53:26.302721Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-09T14:53:26.157442Z","title":"Answer: [NA] Justification: LLM usage did not impact the core methodology, scientific rigorousness, or originality of the research","venue":null,"work_id":"aff28a3f-58c6-46a6-bd21-1f98920f01f9","year":2025},"citing_paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","version":5},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-09T14:53:25.764212Z"},"links":{"citing_paper":"/paper/2502.01618"},"observation_digest":"sha256:9195e5a40d55d396475e64ba0c65f8031c0a4864ac52782aedbd8e2365036de3","observation_id":"4d48cda5-96af-418f-9092-aa029bb5e4e8","resolution":{"observed_at":"2026-08-09T14:53:26.221809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.01618","last_updated":"2025-08-14T07:21:40Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T12:01:19.418738Z","submitted_at":"2025-02-03T18:50:50Z","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":1,"verified_fuzzy":31},"total_outbound_references":50},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 7 inbound Pith citation observations for arXiv:2502.01618."}