{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WJ7USITNSKBVFVMKJWFWR32HZQ","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":"86730c0d7fe12bcfb709083e00a044d33101b58563ae825b42b47d8d38a42abe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-06T01:13:05Z","title_canon_sha256":"f2806b5e897dabf59f122437df64530e85c8827f242219bb6f478a0036bd4122"},"schema_version":"1.0","source":{"id":"2508.06547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06547","created_at":"2026-07-05T11:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06547v1","created_at":"2026-07-05T11:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06547","created_at":"2026-07-05T11:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"WJ7USITNSKBV","created_at":"2026-07-05T11:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"WJ7USITNSKBVFVMK","created_at":"2026-07-05T11:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"WJ7USITN","created_at":"2026-07-05T11:51:02Z"}],"graph_snapshots":[{"event_id":"sha256:0a1bcec01cd74acdc6f62cdf71ac7574a243054ae5c0f58432368115cb6a1105","target":"graph","created_at":"2026-07-05T11:51:02Z","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/2508.06547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional robotic systems typically decompose intelligence into independent modules for computer vision, natural language processing, and motion control. Vision-Language-Action (VLA) models fundamentally transform this approach by employing a single neural network that can simultaneously process visual observations, understand human instructions, and directly output robot actions -- all within a unified framework. However, these systems are highly dependent on high-quality training datasets that can capture the complex relationships between visual observations, language instructions, and rob","authors_text":"Heran Wu, Jingfeng Zhang, Zirun Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-06T01:13:05Z","title":"A tutorial note on collecting simulated data for vision-language-action models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06547","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":"sha256:124e380f7d9743aaf6ec84696070ff91248b9571f5acea2dc9510f9e7dda63cf","target":"record","created_at":"2026-07-05T11:51:02Z","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":"86730c0d7fe12bcfb709083e00a044d33101b58563ae825b42b47d8d38a42abe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-06T01:13:05Z","title_canon_sha256":"f2806b5e897dabf59f122437df64530e85c8827f242219bb6f478a0036bd4122"},"schema_version":"1.0","source":{"id":"2508.06547","kind":"arxiv","version":1}},"canonical_sha256":"b27f49226d928352d58a4d8b68ef47cc1f62f162227796f6f0ed6be9f56b4c1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b27f49226d928352d58a4d8b68ef47cc1f62f162227796f6f0ed6be9f56b4c1d","first_computed_at":"2026-07-05T11:51:02.144670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:02.144670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lf4W+1R+mgbxljFOFEDXoquATUMcax+AtTK0rD7Pa5QY1axIowPkHySYdmvsvYt/vVxWVsTgamnlVpxAdCLlAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:02.145349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:124e380f7d9743aaf6ec84696070ff91248b9571f5acea2dc9510f9e7dda63cf","sha256:0a1bcec01cd74acdc6f62cdf71ac7574a243054ae5c0f58432368115cb6a1105"],"state_sha256":"05eb76359554ef0c89c3a29e8b419f9a053da34bfecaa2ee78f8480783545c3d"}