{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QNLPCPDMMELD2NUVHD3MTLZVWC","short_pith_number":"pith:QNLPCPDM","schema_version":"1.0","canonical_sha256":"8356f13c6c61163d369538f6c9af35b09d65d72ff121fbcdb2a1ffc275d41cc2","source":{"kind":"arxiv","id":"2302.12915","version":2},"attestation_state":"computed","paper":{"title":"Semantic Mechanical Search with Large Vision and Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Brian Ichter, Huang Huang, Kaushik Shivakumar, Ken Goldberg, Lawrence Yunliang Chen, Ryan Hoque, Satvik Sharma","submitted_at":"2023-02-24T22:01:20Z","abstract_excerpt":"Moving objects to find a fully-occluded target object, known as mechanical search, is a challenging problem in robotics. As objects are often organized semantically, we conjecture that semantic information about object relationships can facilitate mechanical search and reduce search time. Large pretrained vision and language models (VLMs and LLMs) have shown promise in generalizing to uncommon objects and previously unseen real-world environments. In this work, we propose a novel framework called Semantic Mechanical Search (SMS). SMS conducts scene understanding and generates a semantic occupa"},"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":"2302.12915","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-02-24T22:01:20Z","cross_cats_sorted":[],"title_canon_sha256":"970178ff84694f79a83b1aac50457d2230ae638ac7b2e573b6cc0c4fc28b971c","abstract_canon_sha256":"6801762cee1499f2785aa2ffbadc8e5c6903c2059da8ce4bd42690e60a01a1f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:07.406526Z","signature_b64":"caUrTWx8OdCY0Syt8MdsfFyaOz6XcW3ZV3ThimnYpr223ojAhb4cbdYB5PX3KGtQrelbXR2btLtjlN5merkZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8356f13c6c61163d369538f6c9af35b09d65d72ff121fbcdb2a1ffc275d41cc2","last_reissued_at":"2026-07-05T07:07:07.405984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:07.405984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Mechanical Search with Large Vision and Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Brian Ichter, Huang Huang, Kaushik Shivakumar, Ken Goldberg, Lawrence Yunliang Chen, Ryan Hoque, Satvik Sharma","submitted_at":"2023-02-24T22:01:20Z","abstract_excerpt":"Moving objects to find a fully-occluded target object, known as mechanical search, is a challenging problem in robotics. As objects are often organized semantically, we conjecture that semantic information about object relationships can facilitate mechanical search and reduce search time. Large pretrained vision and language models (VLMs and LLMs) have shown promise in generalizing to uncommon objects and previously unseen real-world environments. In this work, we propose a novel framework called Semantic Mechanical Search (SMS). SMS conducts scene understanding and generates a semantic occupa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12915","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/2302.12915/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":"2302.12915","created_at":"2026-07-05T07:07:07.406054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12915v2","created_at":"2026-07-05T07:07:07.406054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12915","created_at":"2026-07-05T07:07:07.406054+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNLPCPDMMELD","created_at":"2026-07-05T07:07:07.406054+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNLPCPDMMELD2NUV","created_at":"2026-07-05T07:07:07.406054+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNLPCPDM","created_at":"2026-07-05T07:07:07.406054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20905","citing_title":"Vesta: A Generalist Embodied Reasoning Model","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNLPCPDMMELD2NUVHD3MTLZVWC","json":"https://pith.science/pith/QNLPCPDMMELD2NUVHD3MTLZVWC.json","graph_json":"https://pith.science/api/pith-number/QNLPCPDMMELD2NUVHD3MTLZVWC/graph.json","events_json":"https://pith.science/api/pith-number/QNLPCPDMMELD2NUVHD3MTLZVWC/events.json","paper":"https://pith.science/paper/QNLPCPDM"},"agent_actions":{"view_html":"https://pith.science/pith/QNLPCPDMMELD2NUVHD3MTLZVWC","download_json":"https://pith.science/pith/QNLPCPDMMELD2NUVHD3MTLZVWC.json","view_paper":"https://pith.science/paper/QNLPCPDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12915&json=true","fetch_graph":"https://pith.science/api/pith-number/QNLPCPDMMELD2NUVHD3MTLZVWC/graph.json","fetch_events":"https://pith.science/api/pith-number/QNLPCPDMMELD2NUVHD3MTLZVWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNLPCPDMMELD2NUVHD3MTLZVWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNLPCPDMMELD2NUVHD3MTLZVWC/action/storage_attestation","attest_author":"https://pith.science/pith/QNLPCPDMMELD2NUVHD3MTLZVWC/action/author_attestation","sign_citation":"https://pith.science/pith/QNLPCPDMMELD2NUVHD3MTLZVWC/action/citation_signature","submit_replication":"https://pith.science/pith/QNLPCPDMMELD2NUVHD3MTLZVWC/action/replication_record"}},"created_at":"2026-07-05T07:07:07.406054+00:00","updated_at":"2026-07-05T07:07:07.406054+00:00"}