{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GRP3WIIUS3H3JHHK5LIVYTKOHF","short_pith_number":"pith:GRP3WIIU","schema_version":"1.0","canonical_sha256":"345fbb211496cfb49ceaead15c4d4e397393df247cb3dee3a23d29c966ae1a11","source":{"kind":"arxiv","id":"2606.23623","version":1},"attestation_state":"computed","paper":{"title":"dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haotian Liang, Lei Xu, Mishuo Han, Ran Zheng, Ru Ying, Weijie Shen, Wei Sui, Wenbo Ding, Wenjie Xu, Xiaokang Yang, Xinping Guan, Yao Mu, Yinan Mao, Yitian Liu, Yuhao Wu, Zhongshan Liu","submitted_at":"2026-06-22T17:19:03Z","abstract_excerpt":"Vision-Language-Action (VLA) models have established a powerful paradigm for generalist robotic manipulation by grounding control into the semantic reasoning of VLMs. Prevailing architectures typically model actions continuously via diffusion or flow processes, or discretely through either autoregressive generation or parallel decoding. Recently, Discrete Diffusion VLAs (dVLAs) have emerged as a distinct alternative, unifying vision, language, and action into a single discrete token space via masked generative modeling. While combining iterative refinement with unified representations, its tra"},"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":"2606.23623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-22T17:19:03Z","cross_cats_sorted":[],"title_canon_sha256":"30bfa764093fa969e1261a670b6bef9d3ee6189785b72b253b2b73475eaa71ee","abstract_canon_sha256":"a5fb6833754dab93c25bcbe53e7273268d568e6ea0bf5368eec697f654198af8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:32.630120Z","signature_b64":"wUzkK2BAqIbmFyClphBn9ccr7p9NnBvCyPqPd0ZorDXYR5qbpaOafLMTL6fVC6v1AtG4SBDZkoO5O2V964OjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"345fbb211496cfb49ceaead15c4d4e397393df247cb3dee3a23d29c966ae1a11","last_reissued_at":"2026-06-23T03:14:32.629692Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:32.629692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Haotian Liang, Lei Xu, Mishuo Han, Ran Zheng, Ru Ying, Weijie Shen, Wei Sui, Wenbo Ding, Wenjie Xu, Xiaokang Yang, Xinping Guan, Yao Mu, Yinan Mao, Yitian Liu, Yuhao Wu, Zhongshan Liu","submitted_at":"2026-06-22T17:19:03Z","abstract_excerpt":"Vision-Language-Action (VLA) models have established a powerful paradigm for generalist robotic manipulation by grounding control into the semantic reasoning of VLMs. Prevailing architectures typically model actions continuously via diffusion or flow processes, or discretely through either autoregressive generation or parallel decoding. Recently, Discrete Diffusion VLAs (dVLAs) have emerged as a distinct alternative, unifying vision, language, and action into a single discrete token space via masked generative modeling. While combining iterative refinement with unified representations, its tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23623","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/2606.23623/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":"2606.23623","created_at":"2026-06-23T03:14:32.629750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23623v1","created_at":"2026-06-23T03:14:32.629750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23623","created_at":"2026-06-23T03:14:32.629750+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRP3WIIUS3H3","created_at":"2026-06-23T03:14:32.629750+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRP3WIIUS3H3JHHK","created_at":"2026-06-23T03:14:32.629750+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRP3WIIU","created_at":"2026-06-23T03:14:32.629750+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/GRP3WIIUS3H3JHHK5LIVYTKOHF","json":"https://pith.science/pith/GRP3WIIUS3H3JHHK5LIVYTKOHF.json","graph_json":"https://pith.science/api/pith-number/GRP3WIIUS3H3JHHK5LIVYTKOHF/graph.json","events_json":"https://pith.science/api/pith-number/GRP3WIIUS3H3JHHK5LIVYTKOHF/events.json","paper":"https://pith.science/paper/GRP3WIIU"},"agent_actions":{"view_html":"https://pith.science/pith/GRP3WIIUS3H3JHHK5LIVYTKOHF","download_json":"https://pith.science/pith/GRP3WIIUS3H3JHHK5LIVYTKOHF.json","view_paper":"https://pith.science/paper/GRP3WIIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23623&json=true","fetch_graph":"https://pith.science/api/pith-number/GRP3WIIUS3H3JHHK5LIVYTKOHF/graph.json","fetch_events":"https://pith.science/api/pith-number/GRP3WIIUS3H3JHHK5LIVYTKOHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRP3WIIUS3H3JHHK5LIVYTKOHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRP3WIIUS3H3JHHK5LIVYTKOHF/action/storage_attestation","attest_author":"https://pith.science/pith/GRP3WIIUS3H3JHHK5LIVYTKOHF/action/author_attestation","sign_citation":"https://pith.science/pith/GRP3WIIUS3H3JHHK5LIVYTKOHF/action/citation_signature","submit_replication":"https://pith.science/pith/GRP3WIIUS3H3JHHK5LIVYTKOHF/action/replication_record"}},"created_at":"2026-06-23T03:14:32.629750+00:00","updated_at":"2026-06-23T03:14:32.629750+00:00"}