{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YXPHDCXB2IOUHAEQY5GYGELSLF","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":"e6a242088feb4109a82324fd829eb29e8c9699ec9921468abb51bde308ec3571","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-02-11T02:16:59Z","title_canon_sha256":"2147c89d3ab96aee747be36cc769e99267dd55c0426fdcc3dfb26155b8fb729e"},"schema_version":"1.0","source":{"id":"2502.07837","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07837","created_at":"2026-07-05T10:56:38Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07837v2","created_at":"2026-07-05T10:56:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07837","created_at":"2026-07-05T10:56:38Z"},{"alias_kind":"pith_short_12","alias_value":"YXPHDCXB2IOU","created_at":"2026-07-05T10:56:38Z"},{"alias_kind":"pith_short_16","alias_value":"YXPHDCXB2IOUHAEQ","created_at":"2026-07-05T10:56:38Z"},{"alias_kind":"pith_short_8","alias_value":"YXPHDCXB","created_at":"2026-07-05T10:56:38Z"}],"graph_snapshots":[{"event_id":"sha256:c871ebeb83913bfc651a6bba9a3578c1bb739926828fa1f7179717b4e82335c4","target":"graph","created_at":"2026-07-05T10:56:38Z","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/2502.07837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embodied intelligence seamlessly integrates vision, language, and action.~However, most multimodal robotic models rely on massive fine-tuning, incurring high time and hardware costs.~To address this, we introduce RoboBERT, an end-to-end multimodal manipulation model built around a novel two-stage training paradigm.~In the first stage, we freeze most of the vision encoder and train with a single \"standard\" instruction phrasing, allowing the model to focus on stable policy learning via a CNN-based diffusion policy.~In the second stage, we unfreeze all modules and inject diverse natural language ","authors_text":"Bin Fang, Jianhua Shan, Sheng Liu, Sicheng Wang, Weiheng Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-02-11T02:16:59Z","title":"RoboBERT: An End-to-end Multimodal Robotic Manipulation Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07837","kind":"arxiv","version":2},"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":"sha256:878c5904f665f8225f3231bf20787bc2344d94b313da4c734734b1695db8adbc","target":"record","created_at":"2026-07-05T10:56:38Z","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":"e6a242088feb4109a82324fd829eb29e8c9699ec9921468abb51bde308ec3571","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-02-11T02:16:59Z","title_canon_sha256":"2147c89d3ab96aee747be36cc769e99267dd55c0426fdcc3dfb26155b8fb729e"},"schema_version":"1.0","source":{"id":"2502.07837","kind":"arxiv","version":2}},"canonical_sha256":"c5de718ae1d21d438090c74d831172597943f06d48fffe34710c9abbef75a758","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5de718ae1d21d438090c74d831172597943f06d48fffe34710c9abbef75a758","first_computed_at":"2026-07-05T10:56:38.187030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:38.187030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XonRCaXc9b6lWdIqu2cqYDdPWhy8gBH5XQ89RfGFh5R5E/E0uJ+DuN/yrs63dT8BGzs6bcrwwtg1c/M5LKZOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:38.187674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07837","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:878c5904f665f8225f3231bf20787bc2344d94b313da4c734734b1695db8adbc","sha256:c871ebeb83913bfc651a6bba9a3578c1bb739926828fa1f7179717b4e82335c4"],"state_sha256":"c83d97c26584697685d9bfe7e2695be919cf6acf3c548064e34a6c0510fd931d"}