{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:N64AJMSCB2S55RMXO2TFVAPQ3D","short_pith_number":"pith:N64AJMSC","canonical_record":{"source":{"id":"2606.05296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T18:00:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ca072a1d58eec90375311372c4ff829f7672b056b09026958265e0e9a348eb1","abstract_canon_sha256":"ef30de79ef31780c87d1b1be61e53de427984b2ef0dfed39bbe88ad267a314b5"},"schema_version":"1.0"},"canonical_sha256":"6fb804b2420ea5dec59776a65a81f0d8f3008979e3e03da08a9241f9d4e965ea","source":{"kind":"arxiv","id":"2606.05296","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05296","created_at":"2026-06-05T00:13:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05296v1","created_at":"2026-06-05T00:13:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05296","created_at":"2026-06-05T00:13:52Z"},{"alias_kind":"pith_short_12","alias_value":"N64AJMSCB2S5","created_at":"2026-06-05T00:13:52Z"},{"alias_kind":"pith_short_16","alias_value":"N64AJMSCB2S55RMX","created_at":"2026-06-05T00:13:52Z"},{"alias_kind":"pith_short_8","alias_value":"N64AJMSC","created_at":"2026-06-05T00:13:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:N64AJMSCB2S55RMXO2TFVAPQ3D","target":"record","payload":{"canonical_record":{"source":{"id":"2606.05296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T18:00:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ca072a1d58eec90375311372c4ff829f7672b056b09026958265e0e9a348eb1","abstract_canon_sha256":"ef30de79ef31780c87d1b1be61e53de427984b2ef0dfed39bbe88ad267a314b5"},"schema_version":"1.0"},"canonical_sha256":"6fb804b2420ea5dec59776a65a81f0d8f3008979e3e03da08a9241f9d4e965ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:52.412859Z","signature_b64":"qqx5bxsPoB6pqd9EL7qTn5lzuqBfnhQjRk8EngivN4sPDebfBTfZtE9hqLwj/lrWNHM8rtniPTYLsy7jsC0dBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fb804b2420ea5dec59776a65a81f0d8f3008979e3e03da08a9241f9d4e965ea","last_reissued_at":"2026-06-05T00:13:52.412358Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:52.412358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.05296","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T00:13:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"alEiQxVTkJ0V0Rf525jGmbKeG1F4oktgUouGXZnCsnqSfl0VZfx4vHIxoaFCfta0VS4X27756GS1GZTWFLxyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T21:01:16.452398Z"},"content_sha256":"245cef539770dfed312406c91a2d780f6c54d8a98601b3fb7c445ffc94d3a4a8","schema_version":"1.0","event_id":"sha256:245cef539770dfed312406c91a2d780f6c54d8a98601b3fb7c445ffc94d3a4a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:N64AJMSCB2S55RMXO2TFVAPQ3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anthony L. Caterini, Brendan Leigh Ross, Dae Yon Hwang, Jesse C. Cresswell, No\\\"el Vouitsis, Raunaq Suri, Valentin Villecroze","submitted_at":"2026-06-03T18:00:07Z","abstract_excerpt":"LLM agents operate in two distinct regimes: open-weight agents amenable to reinforcement learning (RL) and black-box agents whose behaviour must be controlled purely at test time. Although black-box agents are often backed by state-of-the-art proprietary LLMs, API-only access precludes parameter-level optimization, rendering most RL methods inapplicable. To address this limitation, we turn to a known equivalence between RL and Bayesian inference. We propose Agentic Monte Carlo (AMC) to directly sample from the optimal policy of a black-box agent rather than training it through RL. The optimal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05296","kind":"arxiv","version":1},"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/2606.05296/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":"2026-06-05T00:13:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eDJo8Cj+1f7a+xeb5r8F7/SFmzfHlVZYrGUEKSmGL6DCcVN5p/IUAhV1erGFFwRrzkxgLGN4c+PJfwigboToAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T21:01:16.453127Z"},"content_sha256":"85becedffad1e626f0ee0b3439050775e9074df8ce35a7963f1f5b4f1931f1dc","schema_version":"1.0","event_id":"sha256:85becedffad1e626f0ee0b3439050775e9074df8ce35a7963f1f5b4f1931f1dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N64AJMSCB2S55RMXO2TFVAPQ3D/bundle.json","state_url":"https://pith.science/pith/N64AJMSCB2S55RMXO2TFVAPQ3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N64AJMSCB2S55RMXO2TFVAPQ3D/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":"2026-06-11T21:01:16Z","links":{"resolver":"https://pith.science/pith/N64AJMSCB2S55RMXO2TFVAPQ3D","bundle":"https://pith.science/pith/N64AJMSCB2S55RMXO2TFVAPQ3D/bundle.json","state":"https://pith.science/pith/N64AJMSCB2S55RMXO2TFVAPQ3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N64AJMSCB2S55RMXO2TFVAPQ3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N64AJMSCB2S55RMXO2TFVAPQ3D","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":"ef30de79ef31780c87d1b1be61e53de427984b2ef0dfed39bbe88ad267a314b5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T18:00:07Z","title_canon_sha256":"2ca072a1d58eec90375311372c4ff829f7672b056b09026958265e0e9a348eb1"},"schema_version":"1.0","source":{"id":"2606.05296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05296","created_at":"2026-06-05T00:13:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05296v1","created_at":"2026-06-05T00:13:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05296","created_at":"2026-06-05T00:13:52Z"},{"alias_kind":"pith_short_12","alias_value":"N64AJMSCB2S5","created_at":"2026-06-05T00:13:52Z"},{"alias_kind":"pith_short_16","alias_value":"N64AJMSCB2S55RMX","created_at":"2026-06-05T00:13:52Z"},{"alias_kind":"pith_short_8","alias_value":"N64AJMSC","created_at":"2026-06-05T00:13:52Z"}],"graph_snapshots":[{"event_id":"sha256:85becedffad1e626f0ee0b3439050775e9074df8ce35a7963f1f5b4f1931f1dc","target":"graph","created_at":"2026-06-05T00:13:52Z","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/2606.05296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM agents operate in two distinct regimes: open-weight agents amenable to reinforcement learning (RL) and black-box agents whose behaviour must be controlled purely at test time. Although black-box agents are often backed by state-of-the-art proprietary LLMs, API-only access precludes parameter-level optimization, rendering most RL methods inapplicable. To address this limitation, we turn to a known equivalence between RL and Bayesian inference. We propose Agentic Monte Carlo (AMC) to directly sample from the optimal policy of a black-box agent rather than training it through RL. The optimal ","authors_text":"Anthony L. Caterini, Brendan Leigh Ross, Dae Yon Hwang, Jesse C. Cresswell, No\\\"el Vouitsis, Raunaq Suri, Valentin Villecroze","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T18:00:07Z","title":"Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05296","kind":"arxiv","version":1},"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":"sha256:245cef539770dfed312406c91a2d780f6c54d8a98601b3fb7c445ffc94d3a4a8","target":"record","created_at":"2026-06-05T00:13:52Z","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":"ef30de79ef31780c87d1b1be61e53de427984b2ef0dfed39bbe88ad267a314b5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T18:00:07Z","title_canon_sha256":"2ca072a1d58eec90375311372c4ff829f7672b056b09026958265e0e9a348eb1"},"schema_version":"1.0","source":{"id":"2606.05296","kind":"arxiv","version":1}},"canonical_sha256":"6fb804b2420ea5dec59776a65a81f0d8f3008979e3e03da08a9241f9d4e965ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fb804b2420ea5dec59776a65a81f0d8f3008979e3e03da08a9241f9d4e965ea","first_computed_at":"2026-06-05T00:13:52.412358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:52.412358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qqx5bxsPoB6pqd9EL7qTn5lzuqBfnhQjRk8EngivN4sPDebfBTfZtE9hqLwj/lrWNHM8rtniPTYLsy7jsC0dBA==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:52.412859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:245cef539770dfed312406c91a2d780f6c54d8a98601b3fb7c445ffc94d3a4a8","sha256:85becedffad1e626f0ee0b3439050775e9074df8ce35a7963f1f5b4f1931f1dc"],"state_sha256":"2daeb79cf1a9cb225d25fde2e639282be18b8d358d4d8ce0b355cfacbb65a3ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GHyPKU6Z83ikXhNIa98IFgkiPInaYQ3h9sMyNdcpUAU+rn0sxzCb5eE9H8XaSauvD/VIlv21zHSoxNaKsczrCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T21:01:16.456404Z","bundle_sha256":"ebf1e438d03e866c53e1f6824a4adffe8018d3d081bcc6c26487104d1f97617c"}}