{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G7W5MR3AWEXRETUXTQ5HJBGUTX","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":"8e32256b00f2d67d5e0ed878bb2ce3d2e023175768d522b16e77544ecb91bd8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-12T09:48:03Z","title_canon_sha256":"80cc590671de51a2c3945f11f150341fe65af7f22893a38349357a1311f8e28d"},"schema_version":"1.0","source":{"id":"2505.07395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07395","created_at":"2026-07-05T11:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07395v1","created_at":"2026-07-05T11:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07395","created_at":"2026-07-05T11:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"G7W5MR3AWEXR","created_at":"2026-07-05T11:01:47Z"},{"alias_kind":"pith_short_16","alias_value":"G7W5MR3AWEXRETUX","created_at":"2026-07-05T11:01:47Z"},{"alias_kind":"pith_short_8","alias_value":"G7W5MR3A","created_at":"2026-07-05T11:01:47Z"}],"graph_snapshots":[{"event_id":"sha256:4976941cd5926ef2a254339937eaf592641ff0b300f7141738554c76cee1d588","target":"graph","created_at":"2026-07-05T11:01:47Z","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/2505.07395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have shown great potential in general robotic decision-making tasks via imitation learning. However, the variable quality of training data often constrains the performance of these models. On the other hand, offline Reinforcement Learning (RL) excels at learning robust policy models from mixed-quality data. In this paper, we introduce Reinforced robot GPT (ReinboT), a novel end-to-end VLA model that integrates the RL principle of maximizing cumulative reward. ReinboT achieves a deeper understanding of the data quality distribution by predicting dense returns","authors_text":"Donglin Wang, Han Zhao, Hongchao Lu, Hongyin Zhang, Pengxiang Ding, Zifeng Zhuang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-12T09:48:03Z","title":"ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07395","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":"sha256:8d784fa9b0921e403261a09da9251d5fa3ce1528c021ce9aa4fa45c273ff0432","target":"record","created_at":"2026-07-05T11:01:47Z","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":"8e32256b00f2d67d5e0ed878bb2ce3d2e023175768d522b16e77544ecb91bd8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-12T09:48:03Z","title_canon_sha256":"80cc590671de51a2c3945f11f150341fe65af7f22893a38349357a1311f8e28d"},"schema_version":"1.0","source":{"id":"2505.07395","kind":"arxiv","version":1}},"canonical_sha256":"37edd64760b12f124e979c3a7484d49de2fe049b5df19558594d7c9f2513b22a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37edd64760b12f124e979c3a7484d49de2fe049b5df19558594d7c9f2513b22a","first_computed_at":"2026-07-05T11:01:47.286469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:47.286469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Ld/iQqhdU89yIS8CMwpG/0ztlDfikL7FJ0Y9wqAdir7Gceyr42Jgggt1g4Vl82BUUnUT5YE1pg9V6eZS66YDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:47.286997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d784fa9b0921e403261a09da9251d5fa3ce1528c021ce9aa4fa45c273ff0432","sha256:4976941cd5926ef2a254339937eaf592641ff0b300f7141738554c76cee1d588"],"state_sha256":"8a5ad0d7a3820fabdd4eb7823cd0973823a08071549c2804fe3a79907a3c62f3"}