{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MQ5QNHU2WGJ5VXONXGYHY4ZJJC","short_pith_number":"pith:MQ5QNHU2","schema_version":"1.0","canonical_sha256":"643b069e9ab193daddcdb9b07c732948b05e109604f1429efdffe655b739f648","source":{"kind":"arxiv","id":"2310.09676","version":2},"attestation_state":"computed","paper":{"title":"Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hangjie Shi, Jiachen Li, Michael Johnston, Qiaozi Gao, Reza Ghanadan, Suhaila Shakiah, William Yang Wang, Xiaofeng Gao, Xuehai He","submitted_at":"2023-10-14T22:24:58Z","abstract_excerpt":"Prompt-based learning has been demonstrated as a compelling paradigm contributing to large language models' tremendous success (LLMs). Inspired by their success in language tasks, existing research has leveraged LLMs in embodied instruction following and task planning. In this work, we tackle the problem of training a robot to understand multimodal prompts, interleaving vision signals with text descriptions. This type of task poses a major challenge to robots' capability to understand the interconnection and complementarity between vision and language signals. In this work, we introduce an eff"},"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":"2310.09676","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-14T22:24:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02d31941a2b5a6f86f01d8da4de80bffe7cf96f82abe9355fb595fbe0764b006","abstract_canon_sha256":"2a5905d63ff7347c8845c5a607596e25a8763e309de24918134696874d28436d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:56.513783Z","signature_b64":"/Q6kGe1z7+zcKRlyun+LcrVgBKskGgQ5fjzCdq5c7HEX9plgaERSAjqxFUdosBmqwls4pVwg8ZC+wVELAGdHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"643b069e9ab193daddcdb9b07c732948b05e109604f1429efdffe655b739f648","last_reissued_at":"2026-07-05T08:23:56.513246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:56.513246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Hangjie Shi, Jiachen Li, Michael Johnston, Qiaozi Gao, Reza Ghanadan, Suhaila Shakiah, William Yang Wang, Xiaofeng Gao, Xuehai He","submitted_at":"2023-10-14T22:24:58Z","abstract_excerpt":"Prompt-based learning has been demonstrated as a compelling paradigm contributing to large language models' tremendous success (LLMs). Inspired by their success in language tasks, existing research has leveraged LLMs in embodied instruction following and task planning. In this work, we tackle the problem of training a robot to understand multimodal prompts, interleaving vision signals with text descriptions. This type of task poses a major challenge to robots' capability to understand the interconnection and complementarity between vision and language signals. In this work, we introduce an eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09676","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/2310.09676/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":"2310.09676","created_at":"2026-07-05T08:23:56.513309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09676v2","created_at":"2026-07-05T08:23:56.513309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09676","created_at":"2026-07-05T08:23:56.513309+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQ5QNHU2WGJ5","created_at":"2026-07-05T08:23:56.513309+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQ5QNHU2WGJ5VXON","created_at":"2026-07-05T08:23:56.513309+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQ5QNHU2","created_at":"2026-07-05T08:23:56.513309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":134,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQ5QNHU2WGJ5VXONXGYHY4ZJJC","json":"https://pith.science/pith/MQ5QNHU2WGJ5VXONXGYHY4ZJJC.json","graph_json":"https://pith.science/api/pith-number/MQ5QNHU2WGJ5VXONXGYHY4ZJJC/graph.json","events_json":"https://pith.science/api/pith-number/MQ5QNHU2WGJ5VXONXGYHY4ZJJC/events.json","paper":"https://pith.science/paper/MQ5QNHU2"},"agent_actions":{"view_html":"https://pith.science/pith/MQ5QNHU2WGJ5VXONXGYHY4ZJJC","download_json":"https://pith.science/pith/MQ5QNHU2WGJ5VXONXGYHY4ZJJC.json","view_paper":"https://pith.science/paper/MQ5QNHU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09676&json=true","fetch_graph":"https://pith.science/api/pith-number/MQ5QNHU2WGJ5VXONXGYHY4ZJJC/graph.json","fetch_events":"https://pith.science/api/pith-number/MQ5QNHU2WGJ5VXONXGYHY4ZJJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQ5QNHU2WGJ5VXONXGYHY4ZJJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQ5QNHU2WGJ5VXONXGYHY4ZJJC/action/storage_attestation","attest_author":"https://pith.science/pith/MQ5QNHU2WGJ5VXONXGYHY4ZJJC/action/author_attestation","sign_citation":"https://pith.science/pith/MQ5QNHU2WGJ5VXONXGYHY4ZJJC/action/citation_signature","submit_replication":"https://pith.science/pith/MQ5QNHU2WGJ5VXONXGYHY4ZJJC/action/replication_record"}},"created_at":"2026-07-05T08:23:56.513309+00:00","updated_at":"2026-07-05T08:23:56.513309+00:00"}