{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5Z7SS22YXSZ4DPSGADNIHIF44E","short_pith_number":"pith:5Z7SS22Y","schema_version":"1.0","canonical_sha256":"ee7f296b58bcb3c1be4600da83a0bce11455f9e4ac243fec9cf64c58a99bab09","source":{"kind":"arxiv","id":"2505.11214","version":1},"attestation_state":"computed","paper":{"title":"Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Gongsheng Li, Han Zhao, Pengxiang Ding, Wei Zhao, Zhefei Gong","submitted_at":"2025-05-16T13:12:08Z","abstract_excerpt":"Vision-Language-Action (VLA) models have recently become highly prominent in the field of robotics. Leveraging vision-language foundation models trained on large-scale internet data, the VLA model can generate robotic actions directly from visual observations and human instructions through a single end-to-end neural network. Despite their effectiveness, current VLA models usually accept only one form of human prompting, language instructions, which may constrain their applicability in open-ended human-robot interactions. For example, a user might expect the robot to retrieve an object shown in"},"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":"2505.11214","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-16T13:12:08Z","cross_cats_sorted":[],"title_canon_sha256":"8f78489baeed9cd0670afa5518a50875406c8c55ceb5aabbe6d8d78d6f7ae00c","abstract_canon_sha256":"5a6eb8bb03d87c0f58f17af79d04dfc412355ee750903ba5902dbf8eefa75cd1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:12.889744Z","signature_b64":"6TxAZK3i0L8VbkSOQjI5mqqAIjQ9R19psxBnMYUkh+IuO+tTpI+FyAV7yJ6nr3QBs+8O8wSWNJ8YtX8Nx7SOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee7f296b58bcb3c1be4600da83a0bce11455f9e4ac243fec9cf64c58a99bab09","last_reissued_at":"2026-07-05T11:04:12.889260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:12.889260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Gongsheng Li, Han Zhao, Pengxiang Ding, Wei Zhao, Zhefei Gong","submitted_at":"2025-05-16T13:12:08Z","abstract_excerpt":"Vision-Language-Action (VLA) models have recently become highly prominent in the field of robotics. Leveraging vision-language foundation models trained on large-scale internet data, the VLA model can generate robotic actions directly from visual observations and human instructions through a single end-to-end neural network. Despite their effectiveness, current VLA models usually accept only one form of human prompting, language instructions, which may constrain their applicability in open-ended human-robot interactions. For example, a user might expect the robot to retrieve an object shown in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11214","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/2505.11214/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":"2505.11214","created_at":"2026-07-05T11:04:12.889324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11214v1","created_at":"2026-07-05T11:04:12.889324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11214","created_at":"2026-07-05T11:04:12.889324+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Z7SS22YXSZ4","created_at":"2026-07-05T11:04:12.889324+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Z7SS22YXSZ4DPSG","created_at":"2026-07-05T11:04:12.889324+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Z7SS22Y","created_at":"2026-07-05T11:04:12.889324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.13073","citing_title":"Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey","ref_index":104,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Z7SS22YXSZ4DPSGADNIHIF44E","json":"https://pith.science/pith/5Z7SS22YXSZ4DPSGADNIHIF44E.json","graph_json":"https://pith.science/api/pith-number/5Z7SS22YXSZ4DPSGADNIHIF44E/graph.json","events_json":"https://pith.science/api/pith-number/5Z7SS22YXSZ4DPSGADNIHIF44E/events.json","paper":"https://pith.science/paper/5Z7SS22Y"},"agent_actions":{"view_html":"https://pith.science/pith/5Z7SS22YXSZ4DPSGADNIHIF44E","download_json":"https://pith.science/pith/5Z7SS22YXSZ4DPSGADNIHIF44E.json","view_paper":"https://pith.science/paper/5Z7SS22Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11214&json=true","fetch_graph":"https://pith.science/api/pith-number/5Z7SS22YXSZ4DPSGADNIHIF44E/graph.json","fetch_events":"https://pith.science/api/pith-number/5Z7SS22YXSZ4DPSGADNIHIF44E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Z7SS22YXSZ4DPSGADNIHIF44E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Z7SS22YXSZ4DPSGADNIHIF44E/action/storage_attestation","attest_author":"https://pith.science/pith/5Z7SS22YXSZ4DPSGADNIHIF44E/action/author_attestation","sign_citation":"https://pith.science/pith/5Z7SS22YXSZ4DPSGADNIHIF44E/action/citation_signature","submit_replication":"https://pith.science/pith/5Z7SS22YXSZ4DPSGADNIHIF44E/action/replication_record"}},"created_at":"2026-07-05T11:04:12.889324+00:00","updated_at":"2026-07-05T11:04:12.889324+00:00"}