{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WJ7USITNSKBVFVMKJWFWR32HZQ","short_pith_number":"pith:WJ7USITN","schema_version":"1.0","canonical_sha256":"b27f49226d928352d58a4d8b68ef47cc1f62f162227796f6f0ed6be9f56b4c1d","source":{"kind":"arxiv","id":"2508.06547","version":1},"attestation_state":"computed","paper":{"title":"A tutorial note on collecting simulated data for vision-language-action models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Heran Wu, Jingfeng Zhang, Zirun Zhou","submitted_at":"2025-08-06T01:13:05Z","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"},"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":"2508.06547","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-06T01:13:05Z","cross_cats_sorted":[],"title_canon_sha256":"f2806b5e897dabf59f122437df64530e85c8827f242219bb6f478a0036bd4122","abstract_canon_sha256":"86730c0d7fe12bcfb709083e00a044d33101b58563ae825b42b47d8d38a42abe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:02.145349Z","signature_b64":"Lf4W+1R+mgbxljFOFEDXoquATUMcax+AtTK0rD7Pa5QY1axIowPkHySYdmvsvYt/vVxWVsTgamnlVpxAdCLlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b27f49226d928352d58a4d8b68ef47cc1f62f162227796f6f0ed6be9f56b4c1d","last_reissued_at":"2026-07-05T11:51:02.144670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:02.144670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A tutorial note on collecting simulated data for vision-language-action models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Heran Wu, Jingfeng Zhang, Zirun Zhou","submitted_at":"2025-08-06T01:13:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06547","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/2508.06547/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":"2508.06547","created_at":"2026-07-05T11:51:02.144763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06547v1","created_at":"2026-07-05T11:51:02.144763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06547","created_at":"2026-07-05T11:51:02.144763+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJ7USITNSKBV","created_at":"2026-07-05T11:51:02.144763+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJ7USITNSKBVFVMK","created_at":"2026-07-05T11:51:02.144763+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJ7USITN","created_at":"2026-07-05T11:51:02.144763+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/WJ7USITNSKBVFVMKJWFWR32HZQ","json":"https://pith.science/pith/WJ7USITNSKBVFVMKJWFWR32HZQ.json","graph_json":"https://pith.science/api/pith-number/WJ7USITNSKBVFVMKJWFWR32HZQ/graph.json","events_json":"https://pith.science/api/pith-number/WJ7USITNSKBVFVMKJWFWR32HZQ/events.json","paper":"https://pith.science/paper/WJ7USITN"},"agent_actions":{"view_html":"https://pith.science/pith/WJ7USITNSKBVFVMKJWFWR32HZQ","download_json":"https://pith.science/pith/WJ7USITNSKBVFVMKJWFWR32HZQ.json","view_paper":"https://pith.science/paper/WJ7USITN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06547&json=true","fetch_graph":"https://pith.science/api/pith-number/WJ7USITNSKBVFVMKJWFWR32HZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WJ7USITNSKBVFVMKJWFWR32HZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJ7USITNSKBVFVMKJWFWR32HZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJ7USITNSKBVFVMKJWFWR32HZQ/action/storage_attestation","attest_author":"https://pith.science/pith/WJ7USITNSKBVFVMKJWFWR32HZQ/action/author_attestation","sign_citation":"https://pith.science/pith/WJ7USITNSKBVFVMKJWFWR32HZQ/action/citation_signature","submit_replication":"https://pith.science/pith/WJ7USITNSKBVFVMKJWFWR32HZQ/action/replication_record"}},"created_at":"2026-07-05T11:51:02.144763+00:00","updated_at":"2026-07-05T11:51:02.144763+00:00"}