{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MYBERLEXUGUXHSCWCXCK5KJ5KM","short_pith_number":"pith:MYBERLEX","schema_version":"1.0","canonical_sha256":"660248ac97a1a973c85615c4aea93d53229f83bf09e0faa5c3abcc8d5bcd492a","source":{"kind":"arxiv","id":"2606.06245","version":1},"attestation_state":"computed","paper":{"title":"MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Boyang Zhang, Lianlei Shan","submitted_at":"2026-06-04T14:48:44Z","abstract_excerpt":"Vision-Language-Action (VLA) policies remain brittle in long-horizon and high-uncertainty control, where one-pass action decoding provides limited inference-time deliberation. Explicit chain-of-thought can increase reasoning depth, but introduces token latency and an indirect text-to-action interface. We propose MPCoT, a reward-guided multi-path latent reasoning framework that initializes $M$ hypotheses, refines them for K weight-tied steps, and softly aggregates them before action decoding. A training-only path-preference objective evaluates candidate action branches with expert-action consis"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.06245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T14:48:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2c30a80062bef9c098803a26376125ec7454231cfb1c5685ecbcba9befe0ec41","abstract_canon_sha256":"25143237f343392c52a8d167ca5092824dfa8879db08efb9d010bd7f1af2b12a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:39.143506Z","signature_b64":"K61eJvO20Nzyz+ikdMGCRLfphYmIkOXzu3qByvsALTbo1W05tPsoRdZUilUN6lHg/b01EBde+KksGeGsoLHgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"660248ac97a1a973c85615c4aea93d53229f83bf09e0faa5c3abcc8d5bcd492a","last_reissued_at":"2026-06-05T01:15:39.143006Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:39.143006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Boyang Zhang, Lianlei Shan","submitted_at":"2026-06-04T14:48:44Z","abstract_excerpt":"Vision-Language-Action (VLA) policies remain brittle in long-horizon and high-uncertainty control, where one-pass action decoding provides limited inference-time deliberation. Explicit chain-of-thought can increase reasoning depth, but introduces token latency and an indirect text-to-action interface. We propose MPCoT, a reward-guided multi-path latent reasoning framework that initializes $M$ hypotheses, refines them for K weight-tied steps, and softly aggregates them before action decoding. A training-only path-preference objective evaluates candidate action branches with expert-action consis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06245","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/2606.06245/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.06245","created_at":"2026-06-05T01:15:39.143076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06245v1","created_at":"2026-06-05T01:15:39.143076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06245","created_at":"2026-06-05T01:15:39.143076+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYBERLEXUGUX","created_at":"2026-06-05T01:15:39.143076+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYBERLEXUGUXHSCW","created_at":"2026-06-05T01:15:39.143076+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYBERLEX","created_at":"2026-06-05T01:15:39.143076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYBERLEXUGUXHSCWCXCK5KJ5KM","json":"https://pith.science/pith/MYBERLEXUGUXHSCWCXCK5KJ5KM.json","graph_json":"https://pith.science/api/pith-number/MYBERLEXUGUXHSCWCXCK5KJ5KM/graph.json","events_json":"https://pith.science/api/pith-number/MYBERLEXUGUXHSCWCXCK5KJ5KM/events.json","paper":"https://pith.science/paper/MYBERLEX"},"agent_actions":{"view_html":"https://pith.science/pith/MYBERLEXUGUXHSCWCXCK5KJ5KM","download_json":"https://pith.science/pith/MYBERLEXUGUXHSCWCXCK5KJ5KM.json","view_paper":"https://pith.science/paper/MYBERLEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06245&json=true","fetch_graph":"https://pith.science/api/pith-number/MYBERLEXUGUXHSCWCXCK5KJ5KM/graph.json","fetch_events":"https://pith.science/api/pith-number/MYBERLEXUGUXHSCWCXCK5KJ5KM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYBERLEXUGUXHSCWCXCK5KJ5KM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYBERLEXUGUXHSCWCXCK5KJ5KM/action/storage_attestation","attest_author":"https://pith.science/pith/MYBERLEXUGUXHSCWCXCK5KJ5KM/action/author_attestation","sign_citation":"https://pith.science/pith/MYBERLEXUGUXHSCWCXCK5KJ5KM/action/citation_signature","submit_replication":"https://pith.science/pith/MYBERLEXUGUXHSCWCXCK5KJ5KM/action/replication_record"}},"created_at":"2026-06-05T01:15:39.143076+00:00","updated_at":"2026-06-05T01:15:39.143076+00:00"}