{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:35PJW4Z5JKTHW2IUZTVFANCMYV","short_pith_number":"pith:35PJW4Z5","schema_version":"1.0","canonical_sha256":"df5e9b733d4aa67b6914ccea50344cc5675f7f3bd35c4d84f39d3b334b4f6341","source":{"kind":"arxiv","id":"2307.03719","version":1},"attestation_state":"computed","paper":{"title":"Polybot: Training One Policy Across Robots While Embracing Variability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Dorsa Sadigh, Jonathan Yang","submitted_at":"2023-07-07T17:21:16Z","abstract_excerpt":"Reusing large datasets is crucial to scale vision-based robotic manipulators to everyday scenarios due to the high cost of collecting robotic datasets. However, robotic platforms possess varying control schemes, camera viewpoints, kinematic configurations, and end-effector morphologies, posing significant challenges when transferring manipulation skills from one platform to another. To tackle this problem, we propose a set of key design decisions to train a single policy for deployment on multiple robotic platforms. Our framework first aligns the observation and action spaces of our policy acr"},"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":"2307.03719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-07-07T17:21:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"853298e45ee91e63bae93647b541e1514a3e78c2c1a11b727eeb0ba5bef8c162","abstract_canon_sha256":"f55f85a01a02060c09a858bee7ddab526ff5dc618a66a7bf946ba91f4a9b29ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:46.614802Z","signature_b64":"/GK12QazyfgX5PAMzBwwz/FRAt0ilSpUGFB8bRB5HAbtaHbATqxBtl8BLKexZLvYo8VEpV1nXHcC9VqsMwMoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df5e9b733d4aa67b6914ccea50344cc5675f7f3bd35c4d84f39d3b334b4f6341","last_reissued_at":"2026-07-05T06:28:46.614356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:46.614356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Polybot: Training One Policy Across Robots While Embracing Variability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Dorsa Sadigh, Jonathan Yang","submitted_at":"2023-07-07T17:21:16Z","abstract_excerpt":"Reusing large datasets is crucial to scale vision-based robotic manipulators to everyday scenarios due to the high cost of collecting robotic datasets. However, robotic platforms possess varying control schemes, camera viewpoints, kinematic configurations, and end-effector morphologies, posing significant challenges when transferring manipulation skills from one platform to another. To tackle this problem, we propose a set of key design decisions to train a single policy for deployment on multiple robotic platforms. Our framework first aligns the observation and action spaces of our policy acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03719","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/2307.03719/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":"2307.03719","created_at":"2026-07-05T06:28:46.614415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03719v1","created_at":"2026-07-05T06:28:46.614415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03719","created_at":"2026-07-05T06:28:46.614415+00:00"},{"alias_kind":"pith_short_12","alias_value":"35PJW4Z5JKTH","created_at":"2026-07-05T06:28:46.614415+00:00"},{"alias_kind":"pith_short_16","alias_value":"35PJW4Z5JKTHW2IU","created_at":"2026-07-05T06:28:46.614415+00:00"},{"alias_kind":"pith_short_8","alias_value":"35PJW4Z5","created_at":"2026-07-05T06:28:46.614415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.08864","citing_title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35PJW4Z5JKTHW2IUZTVFANCMYV","json":"https://pith.science/pith/35PJW4Z5JKTHW2IUZTVFANCMYV.json","graph_json":"https://pith.science/api/pith-number/35PJW4Z5JKTHW2IUZTVFANCMYV/graph.json","events_json":"https://pith.science/api/pith-number/35PJW4Z5JKTHW2IUZTVFANCMYV/events.json","paper":"https://pith.science/paper/35PJW4Z5"},"agent_actions":{"view_html":"https://pith.science/pith/35PJW4Z5JKTHW2IUZTVFANCMYV","download_json":"https://pith.science/pith/35PJW4Z5JKTHW2IUZTVFANCMYV.json","view_paper":"https://pith.science/paper/35PJW4Z5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03719&json=true","fetch_graph":"https://pith.science/api/pith-number/35PJW4Z5JKTHW2IUZTVFANCMYV/graph.json","fetch_events":"https://pith.science/api/pith-number/35PJW4Z5JKTHW2IUZTVFANCMYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35PJW4Z5JKTHW2IUZTVFANCMYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35PJW4Z5JKTHW2IUZTVFANCMYV/action/storage_attestation","attest_author":"https://pith.science/pith/35PJW4Z5JKTHW2IUZTVFANCMYV/action/author_attestation","sign_citation":"https://pith.science/pith/35PJW4Z5JKTHW2IUZTVFANCMYV/action/citation_signature","submit_replication":"https://pith.science/pith/35PJW4Z5JKTHW2IUZTVFANCMYV/action/replication_record"}},"created_at":"2026-07-05T06:28:46.614415+00:00","updated_at":"2026-07-05T06:28:46.614415+00:00"}