{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WC7ENKS4KQHE4YSO272ALEQWQQ","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":"044653cae93167959f60263ae1e19ca09d4abfa6002b64fc70cc4ab2fde53849","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-11T06:01:00Z","title_canon_sha256":"765fb6be6fc182b97a6fdea4e6b934257eddb2e5e8ae49ec0a71f936f9335291"},"schema_version":"1.0","source":{"id":"2508.07650","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07650","created_at":"2026-07-05T11:57:58Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07650v2","created_at":"2026-07-05T11:57:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07650","created_at":"2026-07-05T11:57:58Z"},{"alias_kind":"pith_short_12","alias_value":"WC7ENKS4KQHE","created_at":"2026-07-05T11:57:58Z"},{"alias_kind":"pith_short_16","alias_value":"WC7ENKS4KQHE4YSO","created_at":"2026-07-05T11:57:58Z"},{"alias_kind":"pith_short_8","alias_value":"WC7ENKS4","created_at":"2026-07-05T11:57:58Z"}],"graph_snapshots":[{"event_id":"sha256:50af4997226697f650cb8242bcaa76c09a6f44c0b31b2e431d3c8186d3a24d22","target":"graph","created_at":"2026-07-05T11:57:58Z","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/2508.07650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language-action models have emerged as a crucial paradigm in robotic manipulation. However, existing VLA models exhibit notable limitations in handling ambiguous language instructions and unknown environmental states. Furthermore, their perception is largely constrained to static two-dimensional observations, lacking the capability to model three-dimensional interactions between the robot and its environment. To address these challenges, this paper proposes GraphCoT-VLA, an efficient end-to-end model. To enhance the model's ability to interpret ambiguous instructions and improve task pl","authors_text":"Guowei Huang, Helong Huang, Hong Zhang, Kai Tan, Min Cen, Xingyue Quan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-11T06:01:00Z","title":"GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07650","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":"sha256:4fa6325fde1459eae7e2a81ac044f2d99beaba20307063edacb88c532c92d20b","target":"record","created_at":"2026-07-05T11:57:58Z","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":"044653cae93167959f60263ae1e19ca09d4abfa6002b64fc70cc4ab2fde53849","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-11T06:01:00Z","title_canon_sha256":"765fb6be6fc182b97a6fdea4e6b934257eddb2e5e8ae49ec0a71f936f9335291"},"schema_version":"1.0","source":{"id":"2508.07650","kind":"arxiv","version":2}},"canonical_sha256":"b0be46aa5c540e4e624ed7f405921684345d961f29b88719b0b7db0b63a6ac96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0be46aa5c540e4e624ed7f405921684345d961f29b88719b0b7db0b63a6ac96","first_computed_at":"2026-07-05T11:57:58.639640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:58.639640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eJLvzEXgwC8eR6FH2i2jUccn1cXrQgs8+Lrpso6aS/mIAvJTPODKzlAnG17Y3yikgDRNYKuBaS3pmv2VN77vDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:58.640081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07650","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fa6325fde1459eae7e2a81ac044f2d99beaba20307063edacb88c532c92d20b","sha256:50af4997226697f650cb8242bcaa76c09a6f44c0b31b2e431d3c8186d3a24d22"],"state_sha256":"079ead42dce4e004419dedc4a529e67125070783e86b71527e9352bf9fd90597"}