{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KYSFS7XYC3OKJJJA4SXTPHG5JJ","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":"f89791e4d3a2546d40e47fcb8982c8bae16ec7949a782892ea42f3b83057cd80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-19T07:53:45Z","title_canon_sha256":"349543423140688b5355b790a982a5d929605d876a6bcf5ccd96d5f2e7346b70"},"schema_version":"1.0","source":{"id":"2502.13508","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13508","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13508v2","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13508","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"KYSFS7XYC3OK","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"KYSFS7XYC3OKJJJA","created_at":"2026-07-05T10:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"KYSFS7XY","created_at":"2026-07-05T10:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:47d9b18d95deabefebf531c2e52c3d783f080cfd04a05ab3babc72995ffbd784","target":"graph","created_at":"2026-07-05T10:17:54Z","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/2502.13508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language-action models (VLAs) have become increasingly popular in robot manipulation for their end-to-end design and remarkable performance. However, existing VLAs rely heavily on vision-language models (VLMs) that only support text-based instructions, neglecting the more natural speech modality for human-robot interaction. Traditional speech integration methods usually involves a separate speech recognition system, which complicates the model and introduces error propagation. Moreover, the transcription procedure would lose non-semantic information in the raw speech, such as voiceprint","authors_text":"Donglin Wang, Han Zhao, Min Zhang, Pengxiang Ding, Shuanghao Bai, Wei Zhao, Zhefei Gong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-19T07:53:45Z","title":"VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13508","kind":"arxiv","version":2},"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":"sha256:19eb114eacecbccded2ec21544cf75b4773e84bc10025de65554b52033ae9520","target":"record","created_at":"2026-07-05T10:17:54Z","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":"f89791e4d3a2546d40e47fcb8982c8bae16ec7949a782892ea42f3b83057cd80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-19T07:53:45Z","title_canon_sha256":"349543423140688b5355b790a982a5d929605d876a6bcf5ccd96d5f2e7346b70"},"schema_version":"1.0","source":{"id":"2502.13508","kind":"arxiv","version":2}},"canonical_sha256":"5624597ef816dca4a520e4af379cdd4a4aa6a863b04ac5e6af324c234f15c88b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5624597ef816dca4a520e4af379cdd4a4aa6a863b04ac5e6af324c234f15c88b","first_computed_at":"2026-07-05T10:17:54.743398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:54.743398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5qpgIOS/9pwGR2rSnhS1JBmaoRs/euebTSm14BOdKJSQRI156h6rwN3Wn4RYdILKsO/t8P/gunjvBRHSN5gvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:54.743854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13508","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19eb114eacecbccded2ec21544cf75b4773e84bc10025de65554b52033ae9520","sha256:47d9b18d95deabefebf531c2e52c3d783f080cfd04a05ab3babc72995ffbd784"],"state_sha256":"eb0510eb3c72edebef5f07172f4b788a171e3b38187692d836097a17e179036d"}