{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JRRYBXGSQMTC6SD6ZKMQ6XL3A6","short_pith_number":"pith:JRRYBXGS","schema_version":"1.0","canonical_sha256":"4c6380dcd283262f487eca990f5d7b0785ba5a394d22048f26e0acaa0039a314","source":{"kind":"arxiv","id":"2402.06798","version":3},"attestation_state":"computed","paper":{"title":"Reasoning Grasping via Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jinxuan Xu, Liangjun Zhang, Shiyu Jin, Yutian Lei","submitted_at":"2024-02-09T21:48:19Z","abstract_excerpt":"Despite significant progress in robotic systems for operation within human-centric environments, existing models still heavily rely on explicit human commands to identify and manipulate specific objects. This limits their effectiveness in environments where understanding and acting on implicit human intentions are crucial. In this study, we introduce a novel task: reasoning grasping, where robots need to generate grasp poses based on indirect verbal instructions or intentions. To accomplish this, we propose an end-to-end reasoning grasping model that integrates a multimodal Large Language Mode"},"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":"2402.06798","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-09T21:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"44149e3dcce65752a03d0ba06a548c3764f31030725321dab38eb0e237c28d08","abstract_canon_sha256":"b29886e5ebe1c0ff3e81a982078ce4720df3c7cdfcec4744c2ac533423ba5635"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:40.056956Z","signature_b64":"IofNNyn4l9iLRzMCfhzVFO5+ZRfJoQ5BtFdnm54jwU8QXXlAUB5JQjAnOzMp9uOAgAksmdKR6e4o/MFqq0lpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c6380dcd283262f487eca990f5d7b0785ba5a394d22048f26e0acaa0039a314","last_reissued_at":"2026-07-05T09:20:40.056451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:40.056451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning Grasping via Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jinxuan Xu, Liangjun Zhang, Shiyu Jin, Yutian Lei","submitted_at":"2024-02-09T21:48:19Z","abstract_excerpt":"Despite significant progress in robotic systems for operation within human-centric environments, existing models still heavily rely on explicit human commands to identify and manipulate specific objects. This limits their effectiveness in environments where understanding and acting on implicit human intentions are crucial. In this study, we introduce a novel task: reasoning grasping, where robots need to generate grasp poses based on indirect verbal instructions or intentions. To accomplish this, we propose an end-to-end reasoning grasping model that integrates a multimodal Large Language Mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06798","kind":"arxiv","version":3},"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/2402.06798/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":"2402.06798","created_at":"2026-07-05T09:20:40.056520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06798v3","created_at":"2026-07-05T09:20:40.056520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06798","created_at":"2026-07-05T09:20:40.056520+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRRYBXGSQMTC","created_at":"2026-07-05T09:20:40.056520+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRRYBXGSQMTC6SD6","created_at":"2026-07-05T09:20:40.056520+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRRYBXGS","created_at":"2026-07-05T09:20:40.056520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRRYBXGSQMTC6SD6ZKMQ6XL3A6","json":"https://pith.science/pith/JRRYBXGSQMTC6SD6ZKMQ6XL3A6.json","graph_json":"https://pith.science/api/pith-number/JRRYBXGSQMTC6SD6ZKMQ6XL3A6/graph.json","events_json":"https://pith.science/api/pith-number/JRRYBXGSQMTC6SD6ZKMQ6XL3A6/events.json","paper":"https://pith.science/paper/JRRYBXGS"},"agent_actions":{"view_html":"https://pith.science/pith/JRRYBXGSQMTC6SD6ZKMQ6XL3A6","download_json":"https://pith.science/pith/JRRYBXGSQMTC6SD6ZKMQ6XL3A6.json","view_paper":"https://pith.science/paper/JRRYBXGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06798&json=true","fetch_graph":"https://pith.science/api/pith-number/JRRYBXGSQMTC6SD6ZKMQ6XL3A6/graph.json","fetch_events":"https://pith.science/api/pith-number/JRRYBXGSQMTC6SD6ZKMQ6XL3A6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRRYBXGSQMTC6SD6ZKMQ6XL3A6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRRYBXGSQMTC6SD6ZKMQ6XL3A6/action/storage_attestation","attest_author":"https://pith.science/pith/JRRYBXGSQMTC6SD6ZKMQ6XL3A6/action/author_attestation","sign_citation":"https://pith.science/pith/JRRYBXGSQMTC6SD6ZKMQ6XL3A6/action/citation_signature","submit_replication":"https://pith.science/pith/JRRYBXGSQMTC6SD6ZKMQ6XL3A6/action/replication_record"}},"created_at":"2026-07-05T09:20:40.056520+00:00","updated_at":"2026-07-05T09:20:40.056520+00:00"}