{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5Z7SS22YXSZ4DPSGADNIHIF44E","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":"5a6eb8bb03d87c0f58f17af79d04dfc412355ee750903ba5902dbf8eefa75cd1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-16T13:12:08Z","title_canon_sha256":"8f78489baeed9cd0670afa5518a50875406c8c55ceb5aabbe6d8d78d6f7ae00c"},"schema_version":"1.0","source":{"id":"2505.11214","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11214","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11214v1","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11214","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"5Z7SS22YXSZ4","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"5Z7SS22YXSZ4DPSG","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"5Z7SS22Y","created_at":"2026-07-05T11:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:1fab1a67f8696dd32c6aad7f55aecf0b302f5941636175ee36cbf02e07efbe68","target":"graph","created_at":"2026-07-05T11:04:12Z","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/2505.11214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Donglin Wang, Gongsheng Li, Han Zhao, Pengxiang Ding, Wei Zhao, Zhefei Gong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-16T13:12:08Z","title":"Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11214","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:b9dbd707b36bf14ad2a0305592baf970f99afe68a8acdb0f6be599ae31f59028","target":"record","created_at":"2026-07-05T11:04:12Z","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":"5a6eb8bb03d87c0f58f17af79d04dfc412355ee750903ba5902dbf8eefa75cd1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-16T13:12:08Z","title_canon_sha256":"8f78489baeed9cd0670afa5518a50875406c8c55ceb5aabbe6d8d78d6f7ae00c"},"schema_version":"1.0","source":{"id":"2505.11214","kind":"arxiv","version":1}},"canonical_sha256":"ee7f296b58bcb3c1be4600da83a0bce11455f9e4ac243fec9cf64c58a99bab09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee7f296b58bcb3c1be4600da83a0bce11455f9e4ac243fec9cf64c58a99bab09","first_computed_at":"2026-07-05T11:04:12.889260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:12.889260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6TxAZK3i0L8VbkSOQjI5mqqAIjQ9R19psxBnMYUkh+IuO+tTpI+FyAV7yJ6nr3QBs+8O8wSWNJ8YtX8Nx7SOCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:12.889744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11214","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9dbd707b36bf14ad2a0305592baf970f99afe68a8acdb0f6be599ae31f59028","sha256:1fab1a67f8696dd32c6aad7f55aecf0b302f5941636175ee36cbf02e07efbe68"],"state_sha256":"68d9d454e1e8d53fb1339b7be216b481edff1864caceb900fe5f3ce3349058dd"}