{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z6ELNVS6QHK7W7A2MX4VHWJHM2","short_pith_number":"pith:Z6ELNVS6","canonical_record":{"source":{"id":"2502.01618","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T18:50:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67ff48c5055ea263a48f213e55e6e4e41b55bf641ec9435298c14dea768773b4","abstract_canon_sha256":"d38fc9959936f28bfdb50b78f3605e92677631e9ad71f8a8f46e0ec7eefcb062"},"schema_version":"1.0"},"canonical_sha256":"cf88b6d65e81d5fb7c1a65f953d92766a886238dbb9713fe94d2d15b869361af","source":{"kind":"arxiv","id":"2502.01618","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01618","created_at":"2026-07-05T11:53:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01618v5","created_at":"2026-07-05T11:53:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01618","created_at":"2026-07-05T11:53:43Z"},{"alias_kind":"pith_short_12","alias_value":"Z6ELNVS6QHK7","created_at":"2026-07-05T11:53:43Z"},{"alias_kind":"pith_short_16","alias_value":"Z6ELNVS6QHK7W7A2","created_at":"2026-07-05T11:53:43Z"},{"alias_kind":"pith_short_8","alias_value":"Z6ELNVS6","created_at":"2026-07-05T11:53:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z6ELNVS6QHK7W7A2MX4VHWJHM2","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01618","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T18:50:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67ff48c5055ea263a48f213e55e6e4e41b55bf641ec9435298c14dea768773b4","abstract_canon_sha256":"d38fc9959936f28bfdb50b78f3605e92677631e9ad71f8a8f46e0ec7eefcb062"},"schema_version":"1.0"},"canonical_sha256":"cf88b6d65e81d5fb7c1a65f953d92766a886238dbb9713fe94d2d15b869361af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:43.865368Z","signature_b64":"fVz8FxeE9bMsivHep/hvLXwT/X4FQJn3K5cbhUjtsnYPSPCBpuVfrxQcVt56dX5P3Ih058QuF25zeyx7z4XiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf88b6d65e81d5fb7c1a65f953d92766a886238dbb9713fe94d2d15b869361af","last_reissued_at":"2026-07-05T11:53:43.864859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:43.864859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01618","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:53:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l5YSUFnFXI+DEkM/revX8irjVFcMX3VaM+wrDHLk0qZuYpAAFh/aaPIik/B5/D8MizG2/77V9h4jQKAqWsiaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:02:38.304032Z"},"content_sha256":"578e2e5cf13c24728a42a90ff7e6eb11dfc48e80ad3f19e03b184891da54f061","schema_version":"1.0","event_id":"sha256:578e2e5cf13c24728a42a90ff7e6eb11dfc48e80ad3f19e03b184891da54f061"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z6ELNVS6QHK7W7A2MX4VHWJHM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akash Srivastava, Guangxuan Xu, Isha Puri, Kai Xu, Shivchander Sudalairaj","submitted_at":"2025-02-03T18:50:50Z","abstract_excerpt":"Large language models (LLMs) have achieved significant performance gains via scaling up model sizes and/or data. However, recent evidence suggests diminishing returns from such approaches, motivating scaling the computation spent at inference time. Existing inference-time scaling methods, usually with reward models, cast the task as a search problem, which tends to be vulnerable to reward hacking as a consequence of approximation errors in reward models. In this paper, we instead cast inference-time scaling as a probabilistic inference task and leverage sampling-based techniques to explore the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01618","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.01618/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:53:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fdr385mze/sdDCFiLsGNy+3tCfKsV2kj81Gz7wz8DtEOdodg2jASyhfiR2ndol5TCDMPOzkLyzUH8kXVqCHeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:02:38.304577Z"},"content_sha256":"ce9a210e9c3ec42ab871052d8000e0cc2bebdeaadb6582485f57cca51bd391f3","schema_version":"1.0","event_id":"sha256:ce9a210e9c3ec42ab871052d8000e0cc2bebdeaadb6582485f57cca51bd391f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z6ELNVS6QHK7W7A2MX4VHWJHM2/bundle.json","state_url":"https://pith.science/pith/Z6ELNVS6QHK7W7A2MX4VHWJHM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z6ELNVS6QHK7W7A2MX4VHWJHM2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T02:02:38Z","links":{"resolver":"https://pith.science/pith/Z6ELNVS6QHK7W7A2MX4VHWJHM2","bundle":"https://pith.science/pith/Z6ELNVS6QHK7W7A2MX4VHWJHM2/bundle.json","state":"https://pith.science/pith/Z6ELNVS6QHK7W7A2MX4VHWJHM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z6ELNVS6QHK7W7A2MX4VHWJHM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z6ELNVS6QHK7W7A2MX4VHWJHM2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d38fc9959936f28bfdb50b78f3605e92677631e9ad71f8a8f46e0ec7eefcb062","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T18:50:50Z","title_canon_sha256":"67ff48c5055ea263a48f213e55e6e4e41b55bf641ec9435298c14dea768773b4"},"schema_version":"1.0","source":{"id":"2502.01618","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01618","created_at":"2026-07-05T11:53:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01618v5","created_at":"2026-07-05T11:53:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01618","created_at":"2026-07-05T11:53:43Z"},{"alias_kind":"pith_short_12","alias_value":"Z6ELNVS6QHK7","created_at":"2026-07-05T11:53:43Z"},{"alias_kind":"pith_short_16","alias_value":"Z6ELNVS6QHK7W7A2","created_at":"2026-07-05T11:53:43Z"},{"alias_kind":"pith_short_8","alias_value":"Z6ELNVS6","created_at":"2026-07-05T11:53:43Z"}],"graph_snapshots":[{"event_id":"sha256:ce9a210e9c3ec42ab871052d8000e0cc2bebdeaadb6582485f57cca51bd391f3","target":"graph","created_at":"2026-07-05T11:53:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.01618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved significant performance gains via scaling up model sizes and/or data. However, recent evidence suggests diminishing returns from such approaches, motivating scaling the computation spent at inference time. Existing inference-time scaling methods, usually with reward models, cast the task as a search problem, which tends to be vulnerable to reward hacking as a consequence of approximation errors in reward models. In this paper, we instead cast inference-time scaling as a probabilistic inference task and leverage sampling-based techniques to explore the","authors_text":"Akash Srivastava, Guangxuan Xu, Isha Puri, Kai Xu, Shivchander Sudalairaj","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","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"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01618","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:578e2e5cf13c24728a42a90ff7e6eb11dfc48e80ad3f19e03b184891da54f061","target":"record","created_at":"2026-07-05T11:53:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d38fc9959936f28bfdb50b78f3605e92677631e9ad71f8a8f46e0ec7eefcb062","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T18:50:50Z","title_canon_sha256":"67ff48c5055ea263a48f213e55e6e4e41b55bf641ec9435298c14dea768773b4"},"schema_version":"1.0","source":{"id":"2502.01618","kind":"arxiv","version":5}},"canonical_sha256":"cf88b6d65e81d5fb7c1a65f953d92766a886238dbb9713fe94d2d15b869361af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf88b6d65e81d5fb7c1a65f953d92766a886238dbb9713fe94d2d15b869361af","first_computed_at":"2026-07-05T11:53:43.864859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:43.864859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fVz8FxeE9bMsivHep/hvLXwT/X4FQJn3K5cbhUjtsnYPSPCBpuVfrxQcVt56dX5P3Ih058QuF25zeyx7z4XiCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:43.865368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01618","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:578e2e5cf13c24728a42a90ff7e6eb11dfc48e80ad3f19e03b184891da54f061","sha256:ce9a210e9c3ec42ab871052d8000e0cc2bebdeaadb6582485f57cca51bd391f3"],"state_sha256":"086be7acdcfc750efef475db747a6a2ab27602a095a997da426481df59cb0e95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZrakvI4qDgMojBRSSE3x+4jx7r9NxGwIEkuXC8FQCIlchQHI/9WiZeWuCA1jMCEU+0wD5/96JP6y/6ucijITDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:02:38.309760Z","bundle_sha256":"4ca2751635a47adede94e2187a4d9b26c7d9663d12eb0933bb30b874b34908d5"}}