{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BCYXLEARYWFQQCFVBXKROPUSAQ","short_pith_number":"pith:BCYXLEAR","canonical_record":{"source":{"id":"2605.08982","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T14:54:07Z","cross_cats_sorted":[],"title_canon_sha256":"1edbeafbaed4fbaed6fc7cb04a3969a4c61fe54f4a080b71a0bc2d6082bec347","abstract_canon_sha256":"4957fe21b4e2c176bf8dca54baad63f8fc97eb9b5d5418a5cf19d0353009657f"},"schema_version":"1.0"},"canonical_sha256":"08b1759011c58b0808b50dd5173e92040252eaa0675444e81752221637555da4","source":{"kind":"arxiv","id":"2605.08982","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08982","created_at":"2026-05-22T01:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08982v2","created_at":"2026-05-22T01:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08982","created_at":"2026-05-22T01:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"BCYXLEARYWFQ","created_at":"2026-05-22T01:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"BCYXLEARYWFQQCFV","created_at":"2026-05-22T01:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"BCYXLEAR","created_at":"2026-05-22T01:04:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BCYXLEARYWFQQCFVBXKROPUSAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.08982","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T14:54:07Z","cross_cats_sorted":[],"title_canon_sha256":"1edbeafbaed4fbaed6fc7cb04a3969a4c61fe54f4a080b71a0bc2d6082bec347","abstract_canon_sha256":"4957fe21b4e2c176bf8dca54baad63f8fc97eb9b5d5418a5cf19d0353009657f"},"schema_version":"1.0"},"canonical_sha256":"08b1759011c58b0808b50dd5173e92040252eaa0675444e81752221637555da4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:05.712663Z","signature_b64":"8+sh5wJ/+xgUynBAqHQJoLxXBdSEgGJMktbxsuOBJ/0Kzqhp5peEugkuytfHL8zVyYoY8l9MTU4O14CIWBS1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b1759011c58b0808b50dd5173e92040252eaa0675444e81752221637555da4","last_reissued_at":"2026-05-22T01:04:05.712074Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:05.712074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.08982","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"++pBrI6YhxSg01jiALP7bJ6F2LzudzHfH7TO/MLswjLRwaDSw6tuPhCxjGZlbLzuDeX+RAzkq88BW4qUC1LnBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T13:08:19.504444Z"},"content_sha256":"d2fa718aae6339c42109ac47b2dfc6c80f79c097f86598f07831629bf19b684e","schema_version":"1.0","event_id":"sha256:d2fa718aae6339c42109ac47b2dfc6c80f79c097f86598f07831629bf19b684e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BCYXLEARYWFQQCFVBXKROPUSAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PMCTS: Particle Monte Carlo Tree Search for Principled Parallelized Inference Time Scaling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PMCTS is the first parallel Monte Carlo Tree Search algorithm that preserves formal policy improvement guarantees for neural network evaluations.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hendrik Baier, Joery A. de Vries, Matthijs T. J. Spaan, Viliam Vadocz, Wendelin B\\\"ohmer, Yaniv Oren","submitted_at":"2026-05-09T14:54:07Z","abstract_excerpt":"Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement through search with increasing popularity for real world applications. Due to the sequential and deterministic nature of its search, runtime-scaling of MCTS with parallel compute remains a major challenge. We introduce Particle MCTS (PMCTS), to our knowledge the first principled parallel MCTS algorithm which is suited for neural network evaluations and can preserve formal policy improvement guarantees. Empirically, PMCTS scales well with parallel compute and significantly outperforms the popular heuristic-based bas"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PMCTS is the first principled parallel MCTS algorithm suited for neural network evaluations that preserves formal policy improvement guarantees.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the particle-based parallelization mechanism does not introduce bias or violate the original MCTS convergence properties when neural network evaluations are used.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PMCTS is the first principled parallel MCTS algorithm that preserves formal policy improvement guarantees and scales with parallel compute.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PMCTS is the first parallel Monte Carlo Tree Search algorithm that preserves formal policy improvement guarantees for neural network evaluations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"76b45f5880e07a0b199f3259ca02d143b32bb63acf8f8bd0d2e72f011821393f"},"source":{"id":"2605.08982","kind":"arxiv","version":2},"verdict":{"id":"fc504f06-9493-40dd-805a-6a5f97a5a448","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T02:43:58.437588Z","strongest_claim":"PMCTS is the first principled parallel MCTS algorithm suited for neural network evaluations that preserves formal policy improvement guarantees.","one_line_summary":"PMCTS is the first principled parallel MCTS algorithm that preserves formal policy improvement guarantees and scales with parallel compute.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the particle-based parallelization mechanism does not introduce bias or violate the original MCTS convergence properties when neural network evaluations are used.","pith_extraction_headline":"PMCTS is the first parallel Monte Carlo Tree Search algorithm that preserves formal policy improvement guarantees for neural network evaluations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08982/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T08:42:01.868239Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T20:40:20.332395Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:01:19.451814Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:38:05.327094Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"bffdd71ee078ba629e99f73e739214d8494d47c63d87d4ef78c686b0f0318490"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c08fad4d3553e62c3b38d718f9fff86d8c76a517b360c65577b9ae59ef2a2f9e"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"fc504f06-9493-40dd-805a-6a5f97a5a448"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-22T01:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"94aCMrQjlICqz1H1UBR5XSdRCyjrvjCFGiIA2AJZCag9+m9zGIyualghcR1HNk8QkSULIzGD/w42/w+5+2nfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T13:08:19.505462Z"},"content_sha256":"bd53af6e439ab4ad52e354387746f0f69f07e10b505fcd031ff959b97378f56e","schema_version":"1.0","event_id":"sha256:bd53af6e439ab4ad52e354387746f0f69f07e10b505fcd031ff959b97378f56e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCYXLEARYWFQQCFVBXKROPUSAQ/bundle.json","state_url":"https://pith.science/pith/BCYXLEARYWFQQCFVBXKROPUSAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCYXLEARYWFQQCFVBXKROPUSAQ/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":"2026-06-06T13:08:19Z","links":{"resolver":"https://pith.science/pith/BCYXLEARYWFQQCFVBXKROPUSAQ","bundle":"https://pith.science/pith/BCYXLEARYWFQQCFVBXKROPUSAQ/bundle.json","state":"https://pith.science/pith/BCYXLEARYWFQQCFVBXKROPUSAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCYXLEARYWFQQCFVBXKROPUSAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BCYXLEARYWFQQCFVBXKROPUSAQ","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":"4957fe21b4e2c176bf8dca54baad63f8fc97eb9b5d5418a5cf19d0353009657f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T14:54:07Z","title_canon_sha256":"1edbeafbaed4fbaed6fc7cb04a3969a4c61fe54f4a080b71a0bc2d6082bec347"},"schema_version":"1.0","source":{"id":"2605.08982","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08982","created_at":"2026-05-22T01:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08982v2","created_at":"2026-05-22T01:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08982","created_at":"2026-05-22T01:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"BCYXLEARYWFQ","created_at":"2026-05-22T01:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"BCYXLEARYWFQQCFV","created_at":"2026-05-22T01:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"BCYXLEAR","created_at":"2026-05-22T01:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:bd53af6e439ab4ad52e354387746f0f69f07e10b505fcd031ff959b97378f56e","target":"graph","created_at":"2026-05-22T01:04:05Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"PMCTS is the first principled parallel MCTS algorithm suited for neural network evaluations that preserves formal policy improvement guarantees."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the particle-based parallelization mechanism does not introduce bias or violate the original MCTS convergence properties when neural network evaluations are used."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PMCTS is the first principled parallel MCTS algorithm that preserves formal policy improvement guarantees and scales with parallel compute."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PMCTS is the first parallel Monte Carlo Tree Search algorithm that preserves formal policy improvement guarantees for neural network evaluations."}],"snapshot_sha256":"76b45f5880e07a0b199f3259ca02d143b32bb63acf8f8bd0d2e72f011821393f"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c08fad4d3553e62c3b38d718f9fff86d8c76a517b360c65577b9ae59ef2a2f9e"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T08:42:01.868239Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T20:40:20.332395Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T14:01:19.451814Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T10:38:05.327094Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.08982/integrity.json","findings":[],"snapshot_sha256":"bffdd71ee078ba629e99f73e739214d8494d47c63d87d4ef78c686b0f0318490","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement through search with increasing popularity for real world applications. Due to the sequential and deterministic nature of its search, runtime-scaling of MCTS with parallel compute remains a major challenge. We introduce Particle MCTS (PMCTS), to our knowledge the first principled parallel MCTS algorithm which is suited for neural network evaluations and can preserve formal policy improvement guarantees. Empirically, PMCTS scales well with parallel compute and significantly outperforms the popular heuristic-based bas","authors_text":"Hendrik Baier, Joery A. de Vries, Matthijs T. J. Spaan, Viliam Vadocz, Wendelin B\\\"ohmer, Yaniv Oren","cross_cats":[],"headline":"PMCTS is the first parallel Monte Carlo Tree Search algorithm that preserves formal policy improvement guarantees for neural network evaluations.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T14:54:07Z","title":"PMCTS: Particle Monte Carlo Tree Search for Principled Parallelized Inference Time Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.08982","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T02:43:58.437588Z","id":"fc504f06-9493-40dd-805a-6a5f97a5a448","model_set":{"reader":"grok-4.3"},"one_line_summary":"PMCTS is the first principled parallel MCTS algorithm that preserves formal policy improvement guarantees and scales with parallel compute.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PMCTS is the first parallel Monte Carlo Tree Search algorithm that preserves formal policy improvement guarantees for neural network evaluations.","strongest_claim":"PMCTS is the first principled parallel MCTS algorithm suited for neural network evaluations that preserves formal policy improvement guarantees.","weakest_assumption":"That the particle-based parallelization mechanism does not introduce bias or violate the original MCTS convergence properties when neural network evaluations are used."}},"verdict_id":"fc504f06-9493-40dd-805a-6a5f97a5a448"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d2fa718aae6339c42109ac47b2dfc6c80f79c097f86598f07831629bf19b684e","target":"record","created_at":"2026-05-22T01:04:05Z","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":"4957fe21b4e2c176bf8dca54baad63f8fc97eb9b5d5418a5cf19d0353009657f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T14:54:07Z","title_canon_sha256":"1edbeafbaed4fbaed6fc7cb04a3969a4c61fe54f4a080b71a0bc2d6082bec347"},"schema_version":"1.0","source":{"id":"2605.08982","kind":"arxiv","version":2}},"canonical_sha256":"08b1759011c58b0808b50dd5173e92040252eaa0675444e81752221637555da4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08b1759011c58b0808b50dd5173e92040252eaa0675444e81752221637555da4","first_computed_at":"2026-05-22T01:04:05.712074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:05.712074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8+sh5wJ/+xgUynBAqHQJoLxXBdSEgGJMktbxsuOBJ/0Kzqhp5peEugkuytfHL8zVyYoY8l9MTU4O14CIWBS1DQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:05.712663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08982","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2fa718aae6339c42109ac47b2dfc6c80f79c097f86598f07831629bf19b684e","sha256:bd53af6e439ab4ad52e354387746f0f69f07e10b505fcd031ff959b97378f56e"],"state_sha256":"efe7a01e5a87ca63784e4b25bd62f8637097a57df73f847ce59126dc49ec85a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mEVAHq9QdLUhDmUe9CA2yQMTg6jtYwZvGcx9f1TauJu2HdMkNjzFjdmEH1qTzloKAOJhHbq/BqhuG68K26mHCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T13:08:19.509830Z","bundle_sha256":"abfaf86b3bba828cfa5c62afe6faf00d8d1172fa9583451063c598b241d23ff9"}}