{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SILTR7TUVRKMN5BTJN2NZDV3J3","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":"de021872b8b81fa363b7babfdb2a36f74270dc2df804d506d4fce288f3cbfe68","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-04T13:11:38Z","title_canon_sha256":"100770d8dc0673fdebfd5c0d09ba56b9211072c197c8a3b03174e748039ccd9c"},"schema_version":"1.0","source":{"id":"2412.03293","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03293","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03293v3","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03293","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"pith_short_12","alias_value":"SILTR7TUVRKM","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"pith_short_16","alias_value":"SILTR7TUVRKMN5BT","created_at":"2026-07-05T11:15:40Z"},{"alias_kind":"pith_short_8","alias_value":"SILTR7TU","created_at":"2026-07-05T11:15:40Z"}],"graph_snapshots":[{"event_id":"sha256:a4d50aabbb6a3a15280225f0f6a5002b57fc2665be814ddd7e78d762d1019058","target":"graph","created_at":"2026-07-05T11:15:40Z","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/2412.03293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present DiffusionVLA, a novel framework that seamlessly combines the autoregression model with the diffusion model for learning visuomotor policy. Central to our approach is a next-token prediction objective, enabling the model to reason effectively over the user's query in the context of current observations. Subsequently, a diffusion model is attached to generate robust action outputs. To enhance policy learning through self-reasoning, we introduce a novel reasoning injection module that integrates reasoning phrases directly into the policy learning process. The whole frame","authors_text":"Chaomin Shen, Chengmeng Li, Feifei Feng, Jinming Li, Junjie Wen, Minjie Zhu, Xiaoyu Liu, Yaxin Peng, Yichen Zhu, Zhibin Tang, Zhongyi Zhou","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-04T13:11:38Z","title":"Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03293","kind":"arxiv","version":3},"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:c485636a8be18d71c3fa8716ffaae36d5d6cd98ac30aa20ddf10787107c7a14e","target":"record","created_at":"2026-07-05T11:15:40Z","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":"de021872b8b81fa363b7babfdb2a36f74270dc2df804d506d4fce288f3cbfe68","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-04T13:11:38Z","title_canon_sha256":"100770d8dc0673fdebfd5c0d09ba56b9211072c197c8a3b03174e748039ccd9c"},"schema_version":"1.0","source":{"id":"2412.03293","kind":"arxiv","version":3}},"canonical_sha256":"921738fe74ac54c6f4334b74dc8ebb4ec3fb302952fc7537bbef0010e4e8c9eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"921738fe74ac54c6f4334b74dc8ebb4ec3fb302952fc7537bbef0010e4e8c9eb","first_computed_at":"2026-07-05T11:15:40.887499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:40.887499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r8At97LK4dBK0Es1LGBnZb/dL8zxhUPTQn3ontZzvA0+RugLRQLSj7ceWj6L/bbU9LMuxeC/NnwoJTaCyxYhAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:40.888065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03293","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c485636a8be18d71c3fa8716ffaae36d5d6cd98ac30aa20ddf10787107c7a14e","sha256:a4d50aabbb6a3a15280225f0f6a5002b57fc2665be814ddd7e78d762d1019058"],"state_sha256":"f1116af6be95e0e6874ef8f027fffe012ca65b85ae3af3b68d522bfb17f7230e"}