{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q2LO6JGOZ5CV6SEP5EIREXTBSY","short_pith_number":"pith:Q2LO6JGO","schema_version":"1.0","canonical_sha256":"8696ef24cecf455f488fe911125e6196028289f07438fcfc298d9d366960f79f","source":{"kind":"arxiv","id":"2503.12609","version":2},"attestation_state":"computed","paper":{"title":"VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Di Wen, Edgar Welte, Guanqi Chen, Kunyu Peng, Rainer Stiefelhagen, Rania Rayyes, Sheng Liu, Yitian Shi","submitted_at":"2025-03-16T18:46:54Z","abstract_excerpt":"We propose VISO-Grasp, a novel vision-language-informed system designed to systematically address visibility constraints for grasping in severely occluded environments. By leveraging Foundation Models (FMs) for spatial reasoning and active view planning, our framework constructs and updates an instance-centric representation of spatial relationships, enhancing grasp success under challenging occlusions. Furthermore, this representation facilitates active Next-Best-View (NBV) planning and optimizes sequential grasping strategies when direct grasping is infeasible. Additionally, we introduce a m"},"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":"2503.12609","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-16T18:46:54Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0bcdda1425d3e8ced3058f177bff28bb477797e732778342a170847d83926f39","abstract_canon_sha256":"f24a18d5a6d1c14db3bbe8610d68657083e53431a28349b4e2bd03d2bf35ca38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:08.280659Z","signature_b64":"4Pr2Z3ZSNRzemCUKWmQN3gI+byHNxoyk29CFBgh/WIVxq3Ew6Ilg4cYNSXoXphQZF7X5Tgv4ZnZ8xkzuVneNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8696ef24cecf455f488fe911125e6196028289f07438fcfc298d9d366960f79f","last_reissued_at":"2026-07-05T11:49:08.280076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:08.280076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Di Wen, Edgar Welte, Guanqi Chen, Kunyu Peng, Rainer Stiefelhagen, Rania Rayyes, Sheng Liu, Yitian Shi","submitted_at":"2025-03-16T18:46:54Z","abstract_excerpt":"We propose VISO-Grasp, a novel vision-language-informed system designed to systematically address visibility constraints for grasping in severely occluded environments. By leveraging Foundation Models (FMs) for spatial reasoning and active view planning, our framework constructs and updates an instance-centric representation of spatial relationships, enhancing grasp success under challenging occlusions. Furthermore, this representation facilitates active Next-Best-View (NBV) planning and optimizes sequential grasping strategies when direct grasping is infeasible. Additionally, we introduce a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12609","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/2503.12609/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":"2503.12609","created_at":"2026-07-05T11:49:08.280138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12609v2","created_at":"2026-07-05T11:49:08.280138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12609","created_at":"2026-07-05T11:49:08.280138+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2LO6JGOZ5CV","created_at":"2026-07-05T11:49:08.280138+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2LO6JGOZ5CV6SEP","created_at":"2026-07-05T11:49:08.280138+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2LO6JGO","created_at":"2026-07-05T11:49:08.280138+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12916","citing_title":"RoboRetriever: Single-Camera Robot Object Retrieval via Active and Interactive Perception with Dynamic Scene Graph","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2LO6JGOZ5CV6SEP5EIREXTBSY","json":"https://pith.science/pith/Q2LO6JGOZ5CV6SEP5EIREXTBSY.json","graph_json":"https://pith.science/api/pith-number/Q2LO6JGOZ5CV6SEP5EIREXTBSY/graph.json","events_json":"https://pith.science/api/pith-number/Q2LO6JGOZ5CV6SEP5EIREXTBSY/events.json","paper":"https://pith.science/paper/Q2LO6JGO"},"agent_actions":{"view_html":"https://pith.science/pith/Q2LO6JGOZ5CV6SEP5EIREXTBSY","download_json":"https://pith.science/pith/Q2LO6JGOZ5CV6SEP5EIREXTBSY.json","view_paper":"https://pith.science/paper/Q2LO6JGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12609&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2LO6JGOZ5CV6SEP5EIREXTBSY/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2LO6JGOZ5CV6SEP5EIREXTBSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2LO6JGOZ5CV6SEP5EIREXTBSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2LO6JGOZ5CV6SEP5EIREXTBSY/action/storage_attestation","attest_author":"https://pith.science/pith/Q2LO6JGOZ5CV6SEP5EIREXTBSY/action/author_attestation","sign_citation":"https://pith.science/pith/Q2LO6JGOZ5CV6SEP5EIREXTBSY/action/citation_signature","submit_replication":"https://pith.science/pith/Q2LO6JGOZ5CV6SEP5EIREXTBSY/action/replication_record"}},"created_at":"2026-07-05T11:49:08.280138+00:00","updated_at":"2026-07-05T11:49:08.280138+00:00"}