{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WC7ENKS4KQHE4YSO272ALEQWQQ","short_pith_number":"pith:WC7ENKS4","schema_version":"1.0","canonical_sha256":"b0be46aa5c540e4e624ed7f405921684345d961f29b88719b0b7db0b63a6ac96","source":{"kind":"arxiv","id":"2508.07650","version":2},"attestation_state":"computed","paper":{"title":"GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guowei Huang, Helong Huang, Hong Zhang, Kai Tan, Min Cen, Xingyue Quan","submitted_at":"2025-08-11T06:01:00Z","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"},"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":"2508.07650","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-11T06:01:00Z","cross_cats_sorted":[],"title_canon_sha256":"765fb6be6fc182b97a6fdea4e6b934257eddb2e5e8ae49ec0a71f936f9335291","abstract_canon_sha256":"044653cae93167959f60263ae1e19ca09d4abfa6002b64fc70cc4ab2fde53849"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:58.640081Z","signature_b64":"eJLvzEXgwC8eR6FH2i2jUccn1cXrQgs8+Lrpso6aS/mIAvJTPODKzlAnG17Y3yikgDRNYKuBaS3pmv2VN77vDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0be46aa5c540e4e624ed7f405921684345d961f29b88719b0b7db0b63a6ac96","last_reissued_at":"2026-07-05T11:57:58.639640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:58.639640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guowei Huang, Helong Huang, Hong Zhang, Kai Tan, Min Cen, Xingyue Quan","submitted_at":"2025-08-11T06:01:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07650","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/2508.07650/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":"2508.07650","created_at":"2026-07-05T11:57:58.639696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07650v2","created_at":"2026-07-05T11:57:58.639696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07650","created_at":"2026-07-05T11:57:58.639696+00:00"},{"alias_kind":"pith_short_12","alias_value":"WC7ENKS4KQHE","created_at":"2026-07-05T11:57:58.639696+00:00"},{"alias_kind":"pith_short_16","alias_value":"WC7ENKS4KQHE4YSO","created_at":"2026-07-05T11:57:58.639696+00:00"},{"alias_kind":"pith_short_8","alias_value":"WC7ENKS4","created_at":"2026-07-05T11:57:58.639696+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07107","citing_title":"Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14598","citing_title":"DSSP: Diffusion State Space Policy with Full-History Encoding","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13775","citing_title":"RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12162","citing_title":"X-Imitator: Spatial-Aware Imitation Learning via Bidirectional Action-Pose Interaction","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05714","citing_title":"TriRelVLA: Triadic Relational Structure for Generalizable Embodied Manipulation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09824","citing_title":"ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WC7ENKS4KQHE4YSO272ALEQWQQ","json":"https://pith.science/pith/WC7ENKS4KQHE4YSO272ALEQWQQ.json","graph_json":"https://pith.science/api/pith-number/WC7ENKS4KQHE4YSO272ALEQWQQ/graph.json","events_json":"https://pith.science/api/pith-number/WC7ENKS4KQHE4YSO272ALEQWQQ/events.json","paper":"https://pith.science/paper/WC7ENKS4"},"agent_actions":{"view_html":"https://pith.science/pith/WC7ENKS4KQHE4YSO272ALEQWQQ","download_json":"https://pith.science/pith/WC7ENKS4KQHE4YSO272ALEQWQQ.json","view_paper":"https://pith.science/paper/WC7ENKS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07650&json=true","fetch_graph":"https://pith.science/api/pith-number/WC7ENKS4KQHE4YSO272ALEQWQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WC7ENKS4KQHE4YSO272ALEQWQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WC7ENKS4KQHE4YSO272ALEQWQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WC7ENKS4KQHE4YSO272ALEQWQQ/action/storage_attestation","attest_author":"https://pith.science/pith/WC7ENKS4KQHE4YSO272ALEQWQQ/action/author_attestation","sign_citation":"https://pith.science/pith/WC7ENKS4KQHE4YSO272ALEQWQQ/action/citation_signature","submit_replication":"https://pith.science/pith/WC7ENKS4KQHE4YSO272ALEQWQQ/action/replication_record"}},"created_at":"2026-07-05T11:57:58.639696+00:00","updated_at":"2026-07-05T11:57:58.639696+00:00"}