{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y2CAL7B5POSGY3GXLRDS5PMTTJ","short_pith_number":"pith:Y2CAL7B5","schema_version":"1.0","canonical_sha256":"c68405fc3d7ba46c6cd75c472ebd939a66a1a56b797f85fc7a9543345b3972b8","source":{"kind":"arxiv","id":"2306.11886","version":3},"attestation_state":"computed","paper":{"title":"SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jesse Zhang, Jiahui Zhang, Joseph J. Lim, Karl Pertsch","submitted_at":"2023-06-20T20:59:10Z","abstract_excerpt":"Pre-training robot policies with a rich set of skills can substantially accelerate the learning of downstream tasks. Prior works have defined pre-training tasks via natural language instructions, but doing so requires tedious human annotation of hundreds of thousands of instructions. Thus, we propose SPRINT, a scalable offline policy pre-training approach which substantially reduces the human effort needed for pre-training a diverse set of skills. Our method uses two core ideas to automatically expand a base set of pre-training tasks: instruction relabeling via large language models and cross-"},"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":"2306.11886","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-06-20T20:59:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8ea438bb5ebd25765477403b6a96cf38dfee1ced2a462fc2c79c8a49d0e7737c","abstract_canon_sha256":"93ced2a98b5d663bc30e692c996456b9e28c5775c259814718b5e1561b9b1ac0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:28.705348Z","signature_b64":"1Jm2b6pJYoNjQUnkyTE1wB3f90wLAB92kAtx1L7RuHgHbY0Y7pX2mF5n0meN/SiMk8zrRhHLt2h3MXLhsxPFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c68405fc3d7ba46c6cd75c472ebd939a66a1a56b797f85fc7a9543345b3972b8","last_reissued_at":"2026-07-05T07:38:28.704887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:28.704887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jesse Zhang, Jiahui Zhang, Joseph J. Lim, Karl Pertsch","submitted_at":"2023-06-20T20:59:10Z","abstract_excerpt":"Pre-training robot policies with a rich set of skills can substantially accelerate the learning of downstream tasks. Prior works have defined pre-training tasks via natural language instructions, but doing so requires tedious human annotation of hundreds of thousands of instructions. Thus, we propose SPRINT, a scalable offline policy pre-training approach which substantially reduces the human effort needed for pre-training a diverse set of skills. Our method uses two core ideas to automatically expand a base set of pre-training tasks: instruction relabeling via large language models and cross-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11886","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/2306.11886/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":"2306.11886","created_at":"2026-07-05T07:38:28.704952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11886v3","created_at":"2026-07-05T07:38:28.704952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11886","created_at":"2026-07-05T07:38:28.704952+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y2CAL7B5POSG","created_at":"2026-07-05T07:38:28.704952+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y2CAL7B5POSGY3GX","created_at":"2026-07-05T07:38:28.704952+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y2CAL7B5","created_at":"2026-07-05T07:38:28.704952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.13193","citing_title":"Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y2CAL7B5POSGY3GXLRDS5PMTTJ","json":"https://pith.science/pith/Y2CAL7B5POSGY3GXLRDS5PMTTJ.json","graph_json":"https://pith.science/api/pith-number/Y2CAL7B5POSGY3GXLRDS5PMTTJ/graph.json","events_json":"https://pith.science/api/pith-number/Y2CAL7B5POSGY3GXLRDS5PMTTJ/events.json","paper":"https://pith.science/paper/Y2CAL7B5"},"agent_actions":{"view_html":"https://pith.science/pith/Y2CAL7B5POSGY3GXLRDS5PMTTJ","download_json":"https://pith.science/pith/Y2CAL7B5POSGY3GXLRDS5PMTTJ.json","view_paper":"https://pith.science/paper/Y2CAL7B5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11886&json=true","fetch_graph":"https://pith.science/api/pith-number/Y2CAL7B5POSGY3GXLRDS5PMTTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y2CAL7B5POSGY3GXLRDS5PMTTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y2CAL7B5POSGY3GXLRDS5PMTTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y2CAL7B5POSGY3GXLRDS5PMTTJ/action/storage_attestation","attest_author":"https://pith.science/pith/Y2CAL7B5POSGY3GXLRDS5PMTTJ/action/author_attestation","sign_citation":"https://pith.science/pith/Y2CAL7B5POSGY3GXLRDS5PMTTJ/action/citation_signature","submit_replication":"https://pith.science/pith/Y2CAL7B5POSGY3GXLRDS5PMTTJ/action/replication_record"}},"created_at":"2026-07-05T07:38:28.704952+00:00","updated_at":"2026-07-05T07:38:28.704952+00:00"}