{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MAJZ2LYISESM2CQHYHHJMW7YOW","short_pith_number":"pith:MAJZ2LYI","canonical_record":{"source":{"id":"2506.19850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f4f9a88b96e6f9915d92a4b0f956b73c1c10fb0bb6b7f3cc52c0c2d1f5bc6736","abstract_canon_sha256":"1bd8a3fdd508bb0cf265d5ccedae2c54fb07bdfb83f03b2a81430f293f8619d8"},"schema_version":"1.0"},"canonical_sha256":"60139d2f089124cd0a07c1ce965bf875a581fdd1ea16165b94dcd28e05997ab2","source":{"kind":"arxiv","id":"2506.19850","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19850","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19850v1","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19850","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"MAJZ2LYISESM","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"MAJZ2LYISESM2CQH","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"MAJZ2LYI","created_at":"2026-07-05T11:26:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MAJZ2LYISESM2CQHYHHJMW7YOW","target":"record","payload":{"canonical_record":{"source":{"id":"2506.19850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f4f9a88b96e6f9915d92a4b0f956b73c1c10fb0bb6b7f3cc52c0c2d1f5bc6736","abstract_canon_sha256":"1bd8a3fdd508bb0cf265d5ccedae2c54fb07bdfb83f03b2a81430f293f8619d8"},"schema_version":"1.0"},"canonical_sha256":"60139d2f089124cd0a07c1ce965bf875a581fdd1ea16165b94dcd28e05997ab2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:39.576608Z","signature_b64":"O6P+S5WHmycy1TA73LRihEEBQIqI/2kTKnF4oa5vW1CR1l/9h0aQFBDv60xNDN+lym8HDOd5LdRUraoUglWNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60139d2f089124cd0a07c1ce965bf875a581fdd1ea16165b94dcd28e05997ab2","last_reissued_at":"2026-07-05T11:26:39.576142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:39.576142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.19850","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":"2026-07-05T11:26:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DzyeOXIM4pMggm/KyvHcKv53g+bZTZvR2/HcV3B6Oju8f5UxHpYeqJv44p3k1RlP8VYV92s2D8xVJnCL+oDUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:18:03.907792Z"},"content_sha256":"3abd6ad8fbea23c31bcbf02326b5078d85e75de0cc18d3765c6162dd9c2d72a4","schema_version":"1.0","event_id":"sha256:3abd6ad8fbea23c31bcbf02326b5078d85e75de0cc18d3765c6162dd9c2d72a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MAJZ2LYISESM2CQHYHHJMW7YOW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Vision-Language-Action Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Junbo Zhang, Wenxuan Wang, Xinghang Li, Xinlong Wang, Yingyan Li, Yuntao Chen, Yuqi Wang, Zhaoxiang Zhang","submitted_at":"2025-06-24T17:59:57Z","abstract_excerpt":"Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language models (VLMs) to generate action signals, often overlooking the rich temporal and causal structure embedded in visual observations. In this paper, we present UniVLA, a unified and native multimodal VLA model that autoregressively models vision, language, and action signals as discrete token sequences. This formulation enables flexible multimodal tasks learning,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19850","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/2506.19850/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":"2026-07-05T11:26:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QPCP73+EgvtoR1UzUiY5wH84/v6Cejoip2yzYITt2404nhdnlvLBp+YEpqgtniCVHSzd1OoEalPfGV51hfjUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:18:03.908341Z"},"content_sha256":"0b7dec3704ba0d447b30b370c3f920119cb26bafeb60b2f4e3f00c69cf4dabba","schema_version":"1.0","event_id":"sha256:0b7dec3704ba0d447b30b370c3f920119cb26bafeb60b2f4e3f00c69cf4dabba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MAJZ2LYISESM2CQHYHHJMW7YOW/bundle.json","state_url":"https://pith.science/pith/MAJZ2LYISESM2CQHYHHJMW7YOW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MAJZ2LYISESM2CQHYHHJMW7YOW/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":"2026-08-04T08:18:03Z","links":{"resolver":"https://pith.science/pith/MAJZ2LYISESM2CQHYHHJMW7YOW","bundle":"https://pith.science/pith/MAJZ2LYISESM2CQHYHHJMW7YOW/bundle.json","state":"https://pith.science/pith/MAJZ2LYISESM2CQHYHHJMW7YOW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MAJZ2LYISESM2CQHYHHJMW7YOW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MAJZ2LYISESM2CQHYHHJMW7YOW","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":"1bd8a3fdd508bb0cf265d5ccedae2c54fb07bdfb83f03b2a81430f293f8619d8","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:57Z","title_canon_sha256":"f4f9a88b96e6f9915d92a4b0f956b73c1c10fb0bb6b7f3cc52c0c2d1f5bc6736"},"schema_version":"1.0","source":{"id":"2506.19850","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19850","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19850v1","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19850","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"MAJZ2LYISESM","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"MAJZ2LYISESM2CQH","created_at":"2026-07-05T11:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"MAJZ2LYI","created_at":"2026-07-05T11:26:39Z"}],"graph_snapshots":[{"event_id":"sha256:0b7dec3704ba0d447b30b370c3f920119cb26bafeb60b2f4e3f00c69cf4dabba","target":"graph","created_at":"2026-07-05T11:26:39Z","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/2506.19850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language models (VLMs) to generate action signals, often overlooking the rich temporal and causal structure embedded in visual observations. In this paper, we present UniVLA, a unified and native multimodal VLA model that autoregressively models vision, language, and action signals as discrete token sequences. This formulation enables flexible multimodal tasks learning,","authors_text":"Junbo Zhang, Wenxuan Wang, Xinghang Li, Xinlong Wang, Yingyan Li, Yuntao Chen, Yuqi Wang, Zhaoxiang Zhang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:57Z","title":"Unified Vision-Language-Action Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19850","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":"sha256:3abd6ad8fbea23c31bcbf02326b5078d85e75de0cc18d3765c6162dd9c2d72a4","target":"record","created_at":"2026-07-05T11:26:39Z","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":"1bd8a3fdd508bb0cf265d5ccedae2c54fb07bdfb83f03b2a81430f293f8619d8","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:57Z","title_canon_sha256":"f4f9a88b96e6f9915d92a4b0f956b73c1c10fb0bb6b7f3cc52c0c2d1f5bc6736"},"schema_version":"1.0","source":{"id":"2506.19850","kind":"arxiv","version":1}},"canonical_sha256":"60139d2f089124cd0a07c1ce965bf875a581fdd1ea16165b94dcd28e05997ab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60139d2f089124cd0a07c1ce965bf875a581fdd1ea16165b94dcd28e05997ab2","first_computed_at":"2026-07-05T11:26:39.576142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:39.576142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O6P+S5WHmycy1TA73LRihEEBQIqI/2kTKnF4oa5vW1CR1l/9h0aQFBDv60xNDN+lym8HDOd5LdRUraoUglWNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:39.576608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19850","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3abd6ad8fbea23c31bcbf02326b5078d85e75de0cc18d3765c6162dd9c2d72a4","sha256:0b7dec3704ba0d447b30b370c3f920119cb26bafeb60b2f4e3f00c69cf4dabba"],"state_sha256":"17d11184f99ddf49622051e16ec7317e5e1256e22f043aac902ed649968cbd83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lP5q0cOAgKXi8Qp/Oy8mHmRujGZ9u25xU3DiBLlLnk8rheMnI00r4WHL2k9qysPNAwtJn+cRwhT/FNgkFSZxCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:18:03.912241Z","bundle_sha256":"399ac240aa931f28aa363e04161f93ca6ddec5bb2b6f3b5962b6fd2b45d13f3f"}}