{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2IJT4P2KCZ7XABRQPTE456CAGW","short_pith_number":"pith:2IJT4P2K","schema_version":"1.0","canonical_sha256":"d2133e3f4a167f7006307cc9cef84035be8eb0aa0a2b80c650301b098bff3e9f","source":{"kind":"arxiv","id":"2505.00693","version":3},"attestation_state":"computed","paper":{"title":"Robotic Visual Instruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Guangping Bai, Haolan Kang, Haoyang Li, Xianzheng Ma, Xiaoqi Huang, Yanbang Li, Ziyang Gong","submitted_at":"2025-05-01T17:55:05Z","abstract_excerpt":"Recently, natural language has been the primary medium for human-robot interaction. However, its inherent lack of spatial precision introduces challenges for robotic task definition such as ambiguity and verbosity. Moreover, in some public settings where quiet is required, such as libraries or hospitals, verbal communication with robots is inappropriate. To address these limitations, we introduce the Robotic Visual Instruction (RoVI), a novel paradigm to guide robotic tasks through an object-centric, hand-drawn symbolic representation. RoVI effectively encodes spatial-temporal information into"},"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":"2505.00693","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-01T17:55:05Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c1dbfe651e71501e9ffc9c42ad845d8e180e7895fbdcd80c7b58069c27ec9f2b","abstract_canon_sha256":"0d5beedeedb6d0a423369caedf2b878bb327a83ca7d269989a388d66020d1bef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:05.345393Z","signature_b64":"5j4gm5zcczOSpdF7uz9RbKG5Q1t4xO83Uxf91oDMcDCCcM8Nz1+l+1gHJG0L3Ze6JObo0Zitw+8FlClFrJRTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2133e3f4a167f7006307cc9cef84035be8eb0aa0a2b80c650301b098bff3e9f","last_reissued_at":"2026-07-05T11:44:05.344889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:05.344889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robotic Visual Instruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Guangping Bai, Haolan Kang, Haoyang Li, Xianzheng Ma, Xiaoqi Huang, Yanbang Li, Ziyang Gong","submitted_at":"2025-05-01T17:55:05Z","abstract_excerpt":"Recently, natural language has been the primary medium for human-robot interaction. However, its inherent lack of spatial precision introduces challenges for robotic task definition such as ambiguity and verbosity. Moreover, in some public settings where quiet is required, such as libraries or hospitals, verbal communication with robots is inappropriate. To address these limitations, we introduce the Robotic Visual Instruction (RoVI), a novel paradigm to guide robotic tasks through an object-centric, hand-drawn symbolic representation. RoVI effectively encodes spatial-temporal information into"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00693","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/2505.00693/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":"2505.00693","created_at":"2026-07-05T11:44:05.344952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00693v3","created_at":"2026-07-05T11:44:05.344952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00693","created_at":"2026-07-05T11:44:05.344952+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IJT4P2KCZ7X","created_at":"2026-07-05T11:44:05.344952+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IJT4P2KCZ7XABRQ","created_at":"2026-07-05T11:44:05.344952+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IJT4P2K","created_at":"2026-07-05T11:44:05.344952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22183","citing_title":"Action with Visual Primitives","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2IJT4P2KCZ7XABRQPTE456CAGW","json":"https://pith.science/pith/2IJT4P2KCZ7XABRQPTE456CAGW.json","graph_json":"https://pith.science/api/pith-number/2IJT4P2KCZ7XABRQPTE456CAGW/graph.json","events_json":"https://pith.science/api/pith-number/2IJT4P2KCZ7XABRQPTE456CAGW/events.json","paper":"https://pith.science/paper/2IJT4P2K"},"agent_actions":{"view_html":"https://pith.science/pith/2IJT4P2KCZ7XABRQPTE456CAGW","download_json":"https://pith.science/pith/2IJT4P2KCZ7XABRQPTE456CAGW.json","view_paper":"https://pith.science/paper/2IJT4P2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00693&json=true","fetch_graph":"https://pith.science/api/pith-number/2IJT4P2KCZ7XABRQPTE456CAGW/graph.json","fetch_events":"https://pith.science/api/pith-number/2IJT4P2KCZ7XABRQPTE456CAGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IJT4P2KCZ7XABRQPTE456CAGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IJT4P2KCZ7XABRQPTE456CAGW/action/storage_attestation","attest_author":"https://pith.science/pith/2IJT4P2KCZ7XABRQPTE456CAGW/action/author_attestation","sign_citation":"https://pith.science/pith/2IJT4P2KCZ7XABRQPTE456CAGW/action/citation_signature","submit_replication":"https://pith.science/pith/2IJT4P2KCZ7XABRQPTE456CAGW/action/replication_record"}},"created_at":"2026-07-05T11:44:05.344952+00:00","updated_at":"2026-07-05T11:44:05.344952+00:00"}