{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XNOQTG7TGMRI4HQXCXNKJKDRAV","short_pith_number":"pith:XNOQTG7T","schema_version":"1.0","canonical_sha256":"bb5d099bf333228e1e1715daa4a8710542f65138f6e008a19e60bed11541416a","source":{"kind":"arxiv","id":"2506.19498","version":1},"attestation_state":"computed","paper":{"title":"T-Rex: Task-Adaptive Spatial Representation Extraction for Robotic Manipulation with Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Huiping Zhuang, Qingyao Wu, Shiyi Wang, Wenbo Li, Yiteng Chen","submitted_at":"2025-06-24T10:36:15Z","abstract_excerpt":"Building a general robotic manipulation system capable of performing a wide variety of tasks in real-world settings is a challenging task. Vision-Language Models (VLMs) have demonstrated remarkable potential in robotic manipulation tasks, primarily due to the extensive world knowledge they gain from large-scale datasets. In this process, Spatial Representations (such as points representing object positions or vectors representing object orientations) act as a bridge between VLMs and real-world scene, effectively grounding the reasoning abilities of VLMs and applying them to specific task scena"},"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":"2506.19498","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-24T10:36:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"daccd7a919bdbd9585058300c3e4ffbb43a2a1ab62e0b2e6ae46c8dff086f163","abstract_canon_sha256":"ad4332e40dd77d77340fe5a236fbc91ea7c598d3fdc21725fc28d0e7416c1b3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:33.942698Z","signature_b64":"5A0/xN8Y96wVgPSkdYnUhIoDDXi8c7eCOIBbtuIFjFoBySycbuIc/IVNQKAhGQx+3heoIMoLiZ2gvP6PBbwQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb5d099bf333228e1e1715daa4a8710542f65138f6e008a19e60bed11541416a","last_reissued_at":"2026-07-05T11:26:33.942194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:33.942194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T-Rex: Task-Adaptive Spatial Representation Extraction for Robotic Manipulation with Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Huiping Zhuang, Qingyao Wu, Shiyi Wang, Wenbo Li, Yiteng Chen","submitted_at":"2025-06-24T10:36:15Z","abstract_excerpt":"Building a general robotic manipulation system capable of performing a wide variety of tasks in real-world settings is a challenging task. Vision-Language Models (VLMs) have demonstrated remarkable potential in robotic manipulation tasks, primarily due to the extensive world knowledge they gain from large-scale datasets. In this process, Spatial Representations (such as points representing object positions or vectors representing object orientations) act as a bridge between VLMs and real-world scene, effectively grounding the reasoning abilities of VLMs and applying them to specific task scena"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19498","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/2506.19498/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":"2506.19498","created_at":"2026-07-05T11:26:33.942251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19498v1","created_at":"2026-07-05T11:26:33.942251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19498","created_at":"2026-07-05T11:26:33.942251+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNOQTG7TGMRI","created_at":"2026-07-05T11:26:33.942251+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNOQTG7TGMRI4HQX","created_at":"2026-07-05T11:26:33.942251+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNOQTG7T","created_at":"2026-07-05T11:26:33.942251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNOQTG7TGMRI4HQXCXNKJKDRAV","json":"https://pith.science/pith/XNOQTG7TGMRI4HQXCXNKJKDRAV.json","graph_json":"https://pith.science/api/pith-number/XNOQTG7TGMRI4HQXCXNKJKDRAV/graph.json","events_json":"https://pith.science/api/pith-number/XNOQTG7TGMRI4HQXCXNKJKDRAV/events.json","paper":"https://pith.science/paper/XNOQTG7T"},"agent_actions":{"view_html":"https://pith.science/pith/XNOQTG7TGMRI4HQXCXNKJKDRAV","download_json":"https://pith.science/pith/XNOQTG7TGMRI4HQXCXNKJKDRAV.json","view_paper":"https://pith.science/paper/XNOQTG7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19498&json=true","fetch_graph":"https://pith.science/api/pith-number/XNOQTG7TGMRI4HQXCXNKJKDRAV/graph.json","fetch_events":"https://pith.science/api/pith-number/XNOQTG7TGMRI4HQXCXNKJKDRAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNOQTG7TGMRI4HQXCXNKJKDRAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNOQTG7TGMRI4HQXCXNKJKDRAV/action/storage_attestation","attest_author":"https://pith.science/pith/XNOQTG7TGMRI4HQXCXNKJKDRAV/action/author_attestation","sign_citation":"https://pith.science/pith/XNOQTG7TGMRI4HQXCXNKJKDRAV/action/citation_signature","submit_replication":"https://pith.science/pith/XNOQTG7TGMRI4HQXCXNKJKDRAV/action/replication_record"}},"created_at":"2026-07-05T11:26:33.942251+00:00","updated_at":"2026-07-05T11:26:33.942251+00:00"}