{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OGXU74ZB5BVUP5CUJG7GTZZOFH","short_pith_number":"pith:OGXU74ZB","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"},"canonical_sha256":"71af4ff321e86b47f45449be69e72e29d546b71441df06fca6a8614fee09cc3e","source":{"kind":"arxiv","id":"2606.07895","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07895","created_at":"2026-06-09T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07895v1","created_at":"2026-06-09T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07895","created_at":"2026-06-09T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"OGXU74ZB5BVU","created_at":"2026-06-09T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"OGXU74ZB5BVUP5CU","created_at":"2026-06-09T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"OGXU74ZB","created_at":"2026-06-09T01:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OGXU74ZB5BVUP5CUJG7GTZZOFH","target":"record","payload":{"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"},"canonical_sha256":"71af4ff321e86b47f45449be69e72e29d546b71441df06fca6a8614fee09cc3e","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"},"source_kind":"arxiv","source_id":"2606.07895","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z733hb1vCzr3tsYyKfUbDHRJiILSrvEA/lhmrsUvgsC289TXProxL3DjX/W/YrT8njpRC8d7/v4mLECBp4hwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T17:05:28.295069Z"},"content_sha256":"5885d3d6a1b5f38d2e2e63d72224a4c16f4a53af497adb454b4710ad6b44d8f7","schema_version":"1.0","event_id":"sha256:5885d3d6a1b5f38d2e2e63d72224a4c16f4a53af497adb454b4710ad6b44d8f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OGXU74ZB5BVUP5CUJG7GTZZOFH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3sAmbvD1HiQE6mJqiz4CJWX3Ry2zNDWEi8TCJKVGcUK4+I48e6AwUSZtAFdZdlBPAzywNoZ+N5e0s6OqYKg6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T17:05:28.295455Z"},"content_sha256":"6d958472b0569645feaef659b46f757d3b168ddd55178c1028ec1e29b46d1cad","schema_version":"1.0","event_id":"sha256:6d958472b0569645feaef659b46f757d3b168ddd55178c1028ec1e29b46d1cad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/bundle.json","state_url":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T17:05:28Z","links":{"resolver":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH","bundle":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/bundle.json","state":"https://pith.science/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OGXU74ZB5BVUP5CUJG7GTZZOFH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OGXU74ZB5BVUP5CUJG7GTZZOFH","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":"1023d8cfc6d20feb26394107952a42a9fc44efdd90b4f78f3ed63c78205ed61d","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T23:10:43Z","title_canon_sha256":"bc91281057141dda49cff551c6306fe61bc29c75df1fbce487c4297778f0eea1"},"schema_version":"1.0","source":{"id":"2606.07895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07895","created_at":"2026-06-09T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07895v1","created_at":"2026-06-09T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07895","created_at":"2026-06-09T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"OGXU74ZB5BVU","created_at":"2026-06-09T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"OGXU74ZB5BVUP5CU","created_at":"2026-06-09T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"OGXU74ZB","created_at":"2026-06-09T01:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:6d958472b0569645feaef659b46f757d3b168ddd55178c1028ec1e29b46d1cad","target":"graph","created_at":"2026-06-09T01:04:54Z","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/2606.07895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Sung-Wook Lee, Xuhui Kang, Yen-Ling Kuo","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T23:10:43Z","title":"TBD-VLA: Temporal Block Diffusion Vision Language Action Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07895","kind":"arxiv","version":1},"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":"sha256:5885d3d6a1b5f38d2e2e63d72224a4c16f4a53af497adb454b4710ad6b44d8f7","target":"record","created_at":"2026-06-09T01:04:54Z","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":"1023d8cfc6d20feb26394107952a42a9fc44efdd90b4f78f3ed63c78205ed61d","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T23:10:43Z","title_canon_sha256":"bc91281057141dda49cff551c6306fe61bc29c75df1fbce487c4297778f0eea1"},"schema_version":"1.0","source":{"id":"2606.07895","kind":"arxiv","version":1}},"canonical_sha256":"71af4ff321e86b47f45449be69e72e29d546b71441df06fca6a8614fee09cc3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71af4ff321e86b47f45449be69e72e29d546b71441df06fca6a8614fee09cc3e","first_computed_at":"2026-06-09T01:04:54.762368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:54.762368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T4gJ1GbDwluuXIGiN0CdbrOTOrOrQObClFgGkAjc2GqLiep9Yg6TRJimie+LOQpV/pqZSZR+gizXqTikbR1QCA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:54.762774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5885d3d6a1b5f38d2e2e63d72224a4c16f4a53af497adb454b4710ad6b44d8f7","sha256:6d958472b0569645feaef659b46f757d3b168ddd55178c1028ec1e29b46d1cad"],"state_sha256":"38e3bad6834fefa6f865254f592e569fa0f691b56b3fa0e5a11e06f01b5813fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QzVr5cqGo5XYFkDJpwOx8X+AUsNH3G6ZVvgRBCCganTW7SGTkX56gmZMCfuKUqnKq1nbaQj+JhoErFkmgezDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T17:05:28.297512Z","bundle_sha256":"3b7b26817bef27d4cc43053056cd732e7bce26285df6b4d0a1847eeae678cc8e"}}