{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OGXU74ZB5BVUP5CUJG7GTZZOFH","short_pith_number":"pith:OGXU74ZB","schema_version":"1.0","canonical_sha256":"71af4ff321e86b47f45449be69e72e29d546b71441df06fca6a8614fee09cc3e","source":{"kind":"arxiv","id":"2606.07895","version":1},"attestation_state":"computed","paper":{"title":"TBD-VLA: Temporal Block Diffusion Vision Language Action Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Sung-Wook Lee, Xuhui Kang, Yen-Ling Kuo","submitted_at":"2026-06-05T23:10:43Z","abstract_excerpt":"Discrete Vision-Language-Action (VLA) models typically formulate action generation as next-token prediction over discretized action spaces, conditioning each token autoregressively on prior context. While effective, this paradigm incurs high inference latency and largely ignores the temporal structure inherent in action trajectories. Recent efforts introduce parallel decoding to improve efficiency, enabling faster inference, but lack explicit mechanisms for modeling token dependencies. We introduce TBD-VLA, a discrete token-based VLA framework that incorporates block diffusion to enable tempor"},"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":"2606.07895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T23:10:43Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"bc91281057141dda49cff551c6306fe61bc29c75df1fbce487c4297778f0eea1","abstract_canon_sha256":"1023d8cfc6d20feb26394107952a42a9fc44efdd90b4f78f3ed63c78205ed61d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:54.762774Z","signature_b64":"T4gJ1GbDwluuXIGiN0CdbrOTOrOrQObClFgGkAjc2GqLiep9Yg6TRJimie+LOQpV/pqZSZR+gizXqTikbR1QCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71af4ff321e86b47f45449be69e72e29d546b71441df06fca6a8614fee09cc3e","last_reissued_at":"2026-06-09T01:04:54.762368Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:54.762368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TBD-VLA: Temporal Block Diffusion Vision Language Action Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Sung-Wook Lee, Xuhui Kang, Yen-Ling Kuo","submitted_at":"2026-06-05T23:10:43Z","abstract_excerpt":"Discrete Vision-Language-Action (VLA) models typically formulate action generation as next-token prediction over discretized action spaces, conditioning each token autoregressively on prior context. While effective, this paradigm incurs high inference latency and largely ignores the temporal structure inherent in action trajectories. Recent efforts introduce parallel decoding to improve efficiency, enabling faster inference, but lack explicit mechanisms for modeling token dependencies. We introduce TBD-VLA, a discrete token-based VLA framework that incorporates block diffusion to enable tempor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07895","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/2606.07895/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":"2606.07895","created_at":"2026-06-09T01:04:54.762435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07895v1","created_at":"2026-06-09T01:04:54.762435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07895","created_at":"2026-06-09T01:04:54.762435+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGXU74ZB5BVU","created_at":"2026-06-09T01:04:54.762435+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGXU74ZB5BVUP5CU","created_at":"2026-06-09T01:04:54.762435+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGXU74ZB","created_at":"2026-06-09T01:04:54.762435+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/OGXU74ZB5BVUP5CUJG7GTZZOFH","json":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH.json","graph_json":"https://pith.science/api/pith-number/OGXU74ZB5BVUP5CUJG7GTZZOFH/graph.json","events_json":"https://pith.science/api/pith-number/OGXU74ZB5BVUP5CUJG7GTZZOFH/events.json","paper":"https://pith.science/paper/OGXU74ZB"},"agent_actions":{"view_html":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH","download_json":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH.json","view_paper":"https://pith.science/paper/OGXU74ZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07895&json=true","fetch_graph":"https://pith.science/api/pith-number/OGXU74ZB5BVUP5CUJG7GTZZOFH/graph.json","fetch_events":"https://pith.science/api/pith-number/OGXU74ZB5BVUP5CUJG7GTZZOFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/action/storage_attestation","attest_author":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/action/author_attestation","sign_citation":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/action/citation_signature","submit_replication":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/action/replication_record"}},"created_at":"2026-06-09T01:04:54.762435+00:00","updated_at":"2026-06-09T01:04:54.762435+00:00"}