{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EQSAO3OBCAXJTRG7T6BU6OURVD","short_pith_number":"pith:EQSAO3OB","schema_version":"1.0","canonical_sha256":"2424076dc1102e99c4df9f834f3a91a8cdccb6c5a87df77f365c5ac08c5479a4","source":{"kind":"arxiv","id":"2307.14535","version":2},"attestation_state":"computed","paper":{"title":"Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Huy Ha, Pete Florence, Shuran Song","submitted_at":"2023-07-26T22:52:43Z","abstract_excerpt":"We present a framework for robot skill acquisition, which 1) efficiently scale up data generation of language-labelled robot data and 2) effectively distills this data down into a robust multi-task language-conditioned visuo-motor policy. For (1), we use a large language model (LLM) to guide high-level planning, and sampling-based robot planners (e.g. motion or grasp samplers) for generating diverse and rich manipulation trajectories. To robustify this data-collection process, the LLM also infers a code-snippet for the success condition of each task, simultaneously enabling the data-collection"},"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":"2307.14535","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-26T22:52:43Z","cross_cats_sorted":[],"title_canon_sha256":"b2fb007bc1fc553b271d5a459cc86ffa57b52effaca2e3514dc9ddb84bed0553","abstract_canon_sha256":"f5bc508c8cd17a7d9684692ab47139cef562f1f3abfaa739bb1d28ec0b28444d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:57.693737Z","signature_b64":"0T5PA1tpwTh8CFLjlPVc2SSAFWRI/X5MY02uH63AHdi8niBNuww4Yt0u6gYr/jxShOGPWoVJLmD15snyxXHMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2424076dc1102e99c4df9f834f3a91a8cdccb6c5a87df77f365c5ac08c5479a4","last_reissued_at":"2026-07-05T06:55:57.693266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:57.693266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Huy Ha, Pete Florence, Shuran Song","submitted_at":"2023-07-26T22:52:43Z","abstract_excerpt":"We present a framework for robot skill acquisition, which 1) efficiently scale up data generation of language-labelled robot data and 2) effectively distills this data down into a robust multi-task language-conditioned visuo-motor policy. For (1), we use a large language model (LLM) to guide high-level planning, and sampling-based robot planners (e.g. motion or grasp samplers) for generating diverse and rich manipulation trajectories. To robustify this data-collection process, the LLM also infers a code-snippet for the success condition of each task, simultaneously enabling the data-collection"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14535","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/2307.14535/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":"2307.14535","created_at":"2026-07-05T06:55:57.693323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.14535v2","created_at":"2026-07-05T06:55:57.693323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14535","created_at":"2026-07-05T06:55:57.693323+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQSAO3OBCAXJ","created_at":"2026-07-05T06:55:57.693323+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQSAO3OBCAXJTRG7","created_at":"2026-07-05T06:55:57.693323+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQSAO3OB","created_at":"2026-07-05T06:55:57.693323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24884","citing_title":"InSight: Self-Guided Skill Acquisition via Steerable VLAs","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":241,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":260,"is_internal_anchor":false},{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2312.13139","citing_title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQSAO3OBCAXJTRG7T6BU6OURVD","json":"https://pith.science/pith/EQSAO3OBCAXJTRG7T6BU6OURVD.json","graph_json":"https://pith.science/api/pith-number/EQSAO3OBCAXJTRG7T6BU6OURVD/graph.json","events_json":"https://pith.science/api/pith-number/EQSAO3OBCAXJTRG7T6BU6OURVD/events.json","paper":"https://pith.science/paper/EQSAO3OB"},"agent_actions":{"view_html":"https://pith.science/pith/EQSAO3OBCAXJTRG7T6BU6OURVD","download_json":"https://pith.science/pith/EQSAO3OBCAXJTRG7T6BU6OURVD.json","view_paper":"https://pith.science/paper/EQSAO3OB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.14535&json=true","fetch_graph":"https://pith.science/api/pith-number/EQSAO3OBCAXJTRG7T6BU6OURVD/graph.json","fetch_events":"https://pith.science/api/pith-number/EQSAO3OBCAXJTRG7T6BU6OURVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQSAO3OBCAXJTRG7T6BU6OURVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQSAO3OBCAXJTRG7T6BU6OURVD/action/storage_attestation","attest_author":"https://pith.science/pith/EQSAO3OBCAXJTRG7T6BU6OURVD/action/author_attestation","sign_citation":"https://pith.science/pith/EQSAO3OBCAXJTRG7T6BU6OURVD/action/citation_signature","submit_replication":"https://pith.science/pith/EQSAO3OBCAXJTRG7T6BU6OURVD/action/replication_record"}},"created_at":"2026-07-05T06:55:57.693323+00:00","updated_at":"2026-07-05T06:55:57.693323+00:00"}