{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HH5NQ5SNRRC7NODI52SHR6XUGM","short_pith_number":"pith:HH5NQ5SN","schema_version":"1.0","canonical_sha256":"39fad8764d8c45f6b868eea478faf43324d8de36d2e5bf493c418ae8fedcf412","source":{"kind":"arxiv","id":"2505.06832","version":1},"attestation_state":"computed","paper":{"title":"UniDiffGrasp: A Unified Framework Integrating VLM Reasoning and VLM-Guided Part Diffusion for Open-Vocabulary Constrained Grasping with Dual Arms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bowen Guan, Chengye Song, Hongwei Hu, Jiale Chen, Xueyang Guo, Yu Fu, Zhenze Liu, Zilin Zhao","submitted_at":"2025-05-11T04:05:02Z","abstract_excerpt":"Open-vocabulary, task-oriented grasping of specific functional parts, particularly with dual arms, remains a key challenge, as current Vision-Language Models (VLMs), while enhancing task understanding, often struggle with precise grasp generation within defined constraints and effective dual-arm coordination. We innovatively propose UniDiffGrasp, a unified framework integrating VLM reasoning with guided part diffusion to address these limitations. UniDiffGrasp leverages a VLM to interpret user input and identify semantic targets (object, part(s), mode), which are then grounded via open-vocabul"},"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":"2505.06832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-11T04:05:02Z","cross_cats_sorted":[],"title_canon_sha256":"161f9613424347cbe712315ff15c42edad4aada48507d1b378bf51eac1c817da","abstract_canon_sha256":"21e339a36a926078ab7624d9cb14bee1df15c05dbd3963ff977e5ebf1e729241"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:37.632623Z","signature_b64":"QCmQrJCOOeiZb8qYh0p+V7aK2vstbFUjhUdM0DTMMVDIyPs2PhFCYjq3ogn/RWPAHu9cOpPz9HFs5vbyzkeEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39fad8764d8c45f6b868eea478faf43324d8de36d2e5bf493c418ae8fedcf412","last_reissued_at":"2026-07-05T11:01:37.632151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:37.632151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniDiffGrasp: A Unified Framework Integrating VLM Reasoning and VLM-Guided Part Diffusion for Open-Vocabulary Constrained Grasping with Dual Arms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bowen Guan, Chengye Song, Hongwei Hu, Jiale Chen, Xueyang Guo, Yu Fu, Zhenze Liu, Zilin Zhao","submitted_at":"2025-05-11T04:05:02Z","abstract_excerpt":"Open-vocabulary, task-oriented grasping of specific functional parts, particularly with dual arms, remains a key challenge, as current Vision-Language Models (VLMs), while enhancing task understanding, often struggle with precise grasp generation within defined constraints and effective dual-arm coordination. We innovatively propose UniDiffGrasp, a unified framework integrating VLM reasoning with guided part diffusion to address these limitations. UniDiffGrasp leverages a VLM to interpret user input and identify semantic targets (object, part(s), mode), which are then grounded via open-vocabul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06832","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/2505.06832/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":"2505.06832","created_at":"2026-07-05T11:01:37.632208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06832v1","created_at":"2026-07-05T11:01:37.632208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06832","created_at":"2026-07-05T11:01:37.632208+00:00"},{"alias_kind":"pith_short_12","alias_value":"HH5NQ5SNRRC7","created_at":"2026-07-05T11:01:37.632208+00:00"},{"alias_kind":"pith_short_16","alias_value":"HH5NQ5SNRRC7NODI","created_at":"2026-07-05T11:01:37.632208+00:00"},{"alias_kind":"pith_short_8","alias_value":"HH5NQ5SN","created_at":"2026-07-05T11:01:37.632208+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/HH5NQ5SNRRC7NODI52SHR6XUGM","json":"https://pith.science/pith/HH5NQ5SNRRC7NODI52SHR6XUGM.json","graph_json":"https://pith.science/api/pith-number/HH5NQ5SNRRC7NODI52SHR6XUGM/graph.json","events_json":"https://pith.science/api/pith-number/HH5NQ5SNRRC7NODI52SHR6XUGM/events.json","paper":"https://pith.science/paper/HH5NQ5SN"},"agent_actions":{"view_html":"https://pith.science/pith/HH5NQ5SNRRC7NODI52SHR6XUGM","download_json":"https://pith.science/pith/HH5NQ5SNRRC7NODI52SHR6XUGM.json","view_paper":"https://pith.science/paper/HH5NQ5SN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06832&json=true","fetch_graph":"https://pith.science/api/pith-number/HH5NQ5SNRRC7NODI52SHR6XUGM/graph.json","fetch_events":"https://pith.science/api/pith-number/HH5NQ5SNRRC7NODI52SHR6XUGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HH5NQ5SNRRC7NODI52SHR6XUGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HH5NQ5SNRRC7NODI52SHR6XUGM/action/storage_attestation","attest_author":"https://pith.science/pith/HH5NQ5SNRRC7NODI52SHR6XUGM/action/author_attestation","sign_citation":"https://pith.science/pith/HH5NQ5SNRRC7NODI52SHR6XUGM/action/citation_signature","submit_replication":"https://pith.science/pith/HH5NQ5SNRRC7NODI52SHR6XUGM/action/replication_record"}},"created_at":"2026-07-05T11:01:37.632208+00:00","updated_at":"2026-07-05T11:01:37.632208+00:00"}