{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QVM56BKUITLL6KHPMWP2GAWANZ","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":"9b2368b18b767b43f6f85b76fffe092b5ce2d4e6a02b61bdf9acd3c172541768","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-01T17:59:44Z","title_canon_sha256":"b49b2f5162e514afd61e97db36cb78f2d10797c86f8a0b7b14144a79b7ca5a05"},"schema_version":"1.0","source":{"id":"2507.01016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01016","created_at":"2026-07-05T11:30:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01016v1","created_at":"2026-07-05T11:30:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01016","created_at":"2026-07-05T11:30:19Z"},{"alias_kind":"pith_short_12","alias_value":"QVM56BKUITLL","created_at":"2026-07-05T11:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"QVM56BKUITLL6KHP","created_at":"2026-07-05T11:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"QVM56BKU","created_at":"2026-07-05T11:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:b5729712210dc1af6ff173382e97c45428e751f23a45ae8b547563e1f725d6f7","target":"graph","created_at":"2026-07-05T11:30:19Z","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/2507.01016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce an innovative vector quantization based action tokenizer built upon the largest-scale action trajectory dataset to date, leveraging over 100 times more data than previous approaches. This extensive dataset enables our tokenizer to capture rich spatiotemporal dynamics, resulting in a model that not only accelerates inference but also generates smoother and more coherent action outputs. Once trained, the tokenizer can be seamlessly adapted to a wide range of downstream tasks in a zero-shot manner, from short-horizon reactive behaviors to long-horizon planning. A key f","authors_text":"Hao-Shu Fang, Haoyi Zhu, Jiange Yang, Mingyu Liu, Tong He, Yating Wang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-01T17:59:44Z","title":"VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01016","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:e71c63d1fc24abbe99458d8b28ca8a796f06bb7160405cd22b2bfd67246f8763","target":"record","created_at":"2026-07-05T11:30:19Z","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":"9b2368b18b767b43f6f85b76fffe092b5ce2d4e6a02b61bdf9acd3c172541768","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-01T17:59:44Z","title_canon_sha256":"b49b2f5162e514afd61e97db36cb78f2d10797c86f8a0b7b14144a79b7ca5a05"},"schema_version":"1.0","source":{"id":"2507.01016","kind":"arxiv","version":1}},"canonical_sha256":"8559df055444d6bf28ef659fa302c06e42f1f0171c16f931c3789cc379bc3dfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8559df055444d6bf28ef659fa302c06e42f1f0171c16f931c3789cc379bc3dfe","first_computed_at":"2026-07-05T11:30:19.618547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:19.618547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X4QClZHPA+q2myyv1TLJivKxVpy/xvIJY6gCGW4MruLYHDcpANsSEPBkEm//vVHk7w8IyqSBVSaLkI6KvqQKCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:19.618993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e71c63d1fc24abbe99458d8b28ca8a796f06bb7160405cd22b2bfd67246f8763","sha256:b5729712210dc1af6ff173382e97c45428e751f23a45ae8b547563e1f725d6f7"],"state_sha256":"39e2aba61f703c93100336519a95f3ddaef2bb6be5592783cad81c1b1fb52004"}