{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DCRPXDKDMB7SF2TGU26USXQLZG","short_pith_number":"pith:DCRPXDKD","schema_version":"1.0","canonical_sha256":"18a2fb8d43607f22ea66a6bd495e0bc9b23c702917d29a2a18f2ce561fde733f","source":{"kind":"arxiv","id":"2505.02166","version":1},"attestation_state":"computed","paper":{"title":"CrayonRobo: Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hao Dong, Iaroslav Ponomarenko, Jiahui Xu, Jiaming Liu, Liang Heng, Lingyun Xu, Mingxu Zhang, Shanghang Zhang, Siyuan Huang, Xiaoqi Li, Yan Shen","submitted_at":"2025-05-04T15:58:14Z","abstract_excerpt":"In robotic, task goals can be conveyed through various modalities, such as language, goal images, and goal videos. However, natural language can be ambiguous, while images or videos may offer overly detailed specifications. To tackle these challenges, we introduce CrayonRobo that leverages comprehensive multi-modal prompts that explicitly convey both low-level actions and high-level planning in a simple manner. Specifically, for each key-frame in the task sequence, our method allows for manual or automatic generation of simple and expressive 2D visual prompts overlaid on RGB images. These prom"},"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":"2505.02166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-04T15:58:14Z","cross_cats_sorted":[],"title_canon_sha256":"c9648f280a768a9b0c052b9d06fa819eba77c9b5fa51d8c94f7b1b51618ec4c0","abstract_canon_sha256":"abac50f90975b4d654cbf54939665c24a9ed63f35e8ed5a8f290f230fee40167"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:33.131533Z","signature_b64":"sf9KWQFq8BiW2R/6cAnNMqE+htIEyFiBPkqNAgoXzqbkjt0SI0Jw4WxSE4BYdHImGw28DbvhwpRjwic0JM/NBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18a2fb8d43607f22ea66a6bd495e0bc9b23c702917d29a2a18f2ce561fde733f","last_reissued_at":"2026-07-05T10:58:33.131039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:33.131039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrayonRobo: Object-Centric Prompt-Driven Vision-Language-Action Model for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hao Dong, Iaroslav Ponomarenko, Jiahui Xu, Jiaming Liu, Liang Heng, Lingyun Xu, Mingxu Zhang, Shanghang Zhang, Siyuan Huang, Xiaoqi Li, Yan Shen","submitted_at":"2025-05-04T15:58:14Z","abstract_excerpt":"In robotic, task goals can be conveyed through various modalities, such as language, goal images, and goal videos. However, natural language can be ambiguous, while images or videos may offer overly detailed specifications. To tackle these challenges, we introduce CrayonRobo that leverages comprehensive multi-modal prompts that explicitly convey both low-level actions and high-level planning in a simple manner. Specifically, for each key-frame in the task sequence, our method allows for manual or automatic generation of simple and expressive 2D visual prompts overlaid on RGB images. These prom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02166","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/2505.02166/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":"2505.02166","created_at":"2026-07-05T10:58:33.131098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02166v1","created_at":"2026-07-05T10:58:33.131098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02166","created_at":"2026-07-05T10:58:33.131098+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCRPXDKDMB7S","created_at":"2026-07-05T10:58:33.131098+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCRPXDKDMB7SF2TG","created_at":"2026-07-05T10:58:33.131098+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCRPXDKD","created_at":"2026-07-05T10:58:33.131098+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":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCRPXDKDMB7SF2TGU26USXQLZG","json":"https://pith.science/pith/DCRPXDKDMB7SF2TGU26USXQLZG.json","graph_json":"https://pith.science/api/pith-number/DCRPXDKDMB7SF2TGU26USXQLZG/graph.json","events_json":"https://pith.science/api/pith-number/DCRPXDKDMB7SF2TGU26USXQLZG/events.json","paper":"https://pith.science/paper/DCRPXDKD"},"agent_actions":{"view_html":"https://pith.science/pith/DCRPXDKDMB7SF2TGU26USXQLZG","download_json":"https://pith.science/pith/DCRPXDKDMB7SF2TGU26USXQLZG.json","view_paper":"https://pith.science/paper/DCRPXDKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02166&json=true","fetch_graph":"https://pith.science/api/pith-number/DCRPXDKDMB7SF2TGU26USXQLZG/graph.json","fetch_events":"https://pith.science/api/pith-number/DCRPXDKDMB7SF2TGU26USXQLZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCRPXDKDMB7SF2TGU26USXQLZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCRPXDKDMB7SF2TGU26USXQLZG/action/storage_attestation","attest_author":"https://pith.science/pith/DCRPXDKDMB7SF2TGU26USXQLZG/action/author_attestation","sign_citation":"https://pith.science/pith/DCRPXDKDMB7SF2TGU26USXQLZG/action/citation_signature","submit_replication":"https://pith.science/pith/DCRPXDKDMB7SF2TGU26USXQLZG/action/replication_record"}},"created_at":"2026-07-05T10:58:33.131098+00:00","updated_at":"2026-07-05T10:58:33.131098+00:00"}