{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KA2VX6DZAEGKYDLSJYYE4CTAEP","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":"08056c0c8e2f8fbef47aa7f02bb74912f546096e20d08cdfa71065a928fd4fa2","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-08T17:45:40Z","title_canon_sha256":"e99a280ae5afc020f1c12a37dc3eaa89a84cad1c10a5d4f1f8cdc9b72468a30a"},"schema_version":"1.0","source":{"id":"2509.06932","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06932","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06932v2","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06932","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"pith_short_12","alias_value":"KA2VX6DZAEGK","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"pith_short_16","alias_value":"KA2VX6DZAEGKYDLS","created_at":"2026-07-05T12:08:08Z"},{"alias_kind":"pith_short_8","alias_value":"KA2VX6DZ","created_at":"2026-07-05T12:08:08Z"}],"graph_snapshots":[{"event_id":"sha256:97b226b6b86caf9b772160a3dd24be545be505daa84775c6175e977db5acbac4","target":"graph","created_at":"2026-07-05T12:08:08Z","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/2509.06932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid progress of auto-regressive vision-language models (VLMs) has inspired growing interest in vision-language-action models (VLA) for robotic manipulation. Recently, masked diffusion models, a paradigm distinct from autoregressive models, have begun to demonstrate competitive performance in text generation and multimodal applications, leading to the development of a series of diffusion-based VLMs (d-VLMs). However, leveraging such models for robot policy learning remains largely unexplored. In this work, we present LLaDA-VLA, the first Vision-Language-Diffusion-Action model built upon p","authors_text":"Hebei Li, Kefan Gu, Tiancai Wang, Xiaoyan Sun, Yucheng Zhao, Yuqing Wen","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-08T17:45:40Z","title":"LLaDA-VLA: Vision Language Diffusion Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06932","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:a6b45ad00178523ed634aee92def7a0c9488d666f0208b7571bda18470938d9a","target":"record","created_at":"2026-07-05T12:08:08Z","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":"08056c0c8e2f8fbef47aa7f02bb74912f546096e20d08cdfa71065a928fd4fa2","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-09-08T17:45:40Z","title_canon_sha256":"e99a280ae5afc020f1c12a37dc3eaa89a84cad1c10a5d4f1f8cdc9b72468a30a"},"schema_version":"1.0","source":{"id":"2509.06932","kind":"arxiv","version":2}},"canonical_sha256":"50355bf879010cac0d724e304e0a6023c4e5f4540537dc5d3350051a7c8bd64e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50355bf879010cac0d724e304e0a6023c4e5f4540537dc5d3350051a7c8bd64e","first_computed_at":"2026-07-05T12:08:08.457795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:08.457795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xQg2XJnyh4Ui7braXlTaYx2c4OoDbc5iWZummNof+raGxLucVw840HeZaxEaiVVgCXQCNkKh3WGoV7hlltl0BA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:08.458390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06932","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6b45ad00178523ed634aee92def7a0c9488d666f0208b7571bda18470938d9a","sha256:97b226b6b86caf9b772160a3dd24be545be505daa84775c6175e977db5acbac4"],"state_sha256":"f8a283928145aca5e556198f9624b54609ca30539dff0d016685f7d49ebc98ee"}