{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KYSFS7XYC3OKJJJA4SXTPHG5JJ","short_pith_number":"pith:KYSFS7XY","schema_version":"1.0","canonical_sha256":"5624597ef816dca4a520e4af379cdd4a4aa6a863b04ac5e6af324c234f15c88b","source":{"kind":"arxiv","id":"2502.13508","version":2},"attestation_state":"computed","paper":{"title":"VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Han Zhao, Min Zhang, Pengxiang Ding, Shuanghao Bai, Wei Zhao, Zhefei Gong","submitted_at":"2025-02-19T07:53:45Z","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"},"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":"2502.13508","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-19T07:53:45Z","cross_cats_sorted":[],"title_canon_sha256":"349543423140688b5355b790a982a5d929605d876a6bcf5ccd96d5f2e7346b70","abstract_canon_sha256":"f89791e4d3a2546d40e47fcb8982c8bae16ec7949a782892ea42f3b83057cd80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:54.743854Z","signature_b64":"5qpgIOS/9pwGR2rSnhS1JBmaoRs/euebTSm14BOdKJSQRI156h6rwN3Wn4RYdILKsO/t8P/gunjvBRHSN5gvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5624597ef816dca4a520e4af379cdd4a4aa6a863b04ac5e6af324c234f15c88b","last_reissued_at":"2026-07-05T10:17:54.743398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:54.743398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Han Zhao, Min Zhang, Pengxiang Ding, Shuanghao Bai, Wei Zhao, Zhefei Gong","submitted_at":"2025-02-19T07:53:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13508","kind":"arxiv","version":2},"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/2502.13508/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":"2502.13508","created_at":"2026-07-05T10:17:54.743463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13508v2","created_at":"2026-07-05T10:17:54.743463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13508","created_at":"2026-07-05T10:17:54.743463+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYSFS7XYC3OK","created_at":"2026-07-05T10:17:54.743463+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYSFS7XYC3OKJJJA","created_at":"2026-07-05T10:17:54.743463+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYSFS7XY","created_at":"2026-07-05T10:17:54.743463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24633","citing_title":"Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17598","citing_title":"MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25044","citing_title":"ThermoAct:Thermal-Aware Vision-Language-Action Models for Robotic Perception and Decision-Making","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05855","citing_title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10821","citing_title":"UniSteer: Unified Noise Steering for Efficient Human-Guided VLA Adaptation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22152","citing_title":"dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYSFS7XYC3OKJJJA4SXTPHG5JJ","json":"https://pith.science/pith/KYSFS7XYC3OKJJJA4SXTPHG5JJ.json","graph_json":"https://pith.science/api/pith-number/KYSFS7XYC3OKJJJA4SXTPHG5JJ/graph.json","events_json":"https://pith.science/api/pith-number/KYSFS7XYC3OKJJJA4SXTPHG5JJ/events.json","paper":"https://pith.science/paper/KYSFS7XY"},"agent_actions":{"view_html":"https://pith.science/pith/KYSFS7XYC3OKJJJA4SXTPHG5JJ","download_json":"https://pith.science/pith/KYSFS7XYC3OKJJJA4SXTPHG5JJ.json","view_paper":"https://pith.science/paper/KYSFS7XY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13508&json=true","fetch_graph":"https://pith.science/api/pith-number/KYSFS7XYC3OKJJJA4SXTPHG5JJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KYSFS7XYC3OKJJJA4SXTPHG5JJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYSFS7XYC3OKJJJA4SXTPHG5JJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYSFS7XYC3OKJJJA4SXTPHG5JJ/action/storage_attestation","attest_author":"https://pith.science/pith/KYSFS7XYC3OKJJJA4SXTPHG5JJ/action/author_attestation","sign_citation":"https://pith.science/pith/KYSFS7XYC3OKJJJA4SXTPHG5JJ/action/citation_signature","submit_replication":"https://pith.science/pith/KYSFS7XYC3OKJJJA4SXTPHG5JJ/action/replication_record"}},"created_at":"2026-07-05T10:17:54.743463+00:00","updated_at":"2026-07-05T10:17:54.743463+00:00"}