{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MROC5BMTXKCPMRFKJLPDOQDHQG","short_pith_number":"pith:MROC5BMT","schema_version":"1.0","canonical_sha256":"645c2e8593ba84f644aa4ade374067818cf2f9c46b459546fa140a90341f33d4","source":{"kind":"arxiv","id":"2410.22332","version":2},"attestation_state":"computed","paper":{"title":"Local Policies Enable Zero-shot Long-horizon Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chen Chen, Deepak Pathak, Jian Zhang, Min Liu, Murtaza Dalal, Ruslan Salakhutdinov, Walter Talbott","submitted_at":"2024-10-29T17:59:55Z","abstract_excerpt":"Sim2real for robotic manipulation is difficult due to the challenges of simulating complex contacts and generating realistic task distributions. To tackle the latter problem, we introduce ManipGen, which leverages a new class of policies for sim2real transfer: local policies. Locality enables a variety of appealing properties including invariances to absolute robot and object pose, skill ordering, and global scene configuration. We combine these policies with foundation models for vision, language and motion planning and demonstrate SOTA zero-shot performance of our method to Robosuite benchma"},"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":"2410.22332","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-29T17:59:55Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"42e3fcb8883473ec98baa11619363c719ce3f70bec3c499167f1709ec3f300dd","abstract_canon_sha256":"a2bcab97d91a08ca4cbf7c313d84d5cce3ae66cbebf0b718e0f49173f96e1e8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:18.457436Z","signature_b64":"/E88telW3mIUnVgtGtkeSvxLJ8Wvp2rxk5KR5YDNlSEtPHEJ6vsFRzNjWteDL7tToe78x8ipI3IfMG0g6I+IBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"645c2e8593ba84f644aa4ade374067818cf2f9c46b459546fa140a90341f33d4","last_reissued_at":"2026-07-05T10:27:18.456943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:18.456943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Policies Enable Zero-shot Long-horizon Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chen Chen, Deepak Pathak, Jian Zhang, Min Liu, Murtaza Dalal, Ruslan Salakhutdinov, Walter Talbott","submitted_at":"2024-10-29T17:59:55Z","abstract_excerpt":"Sim2real for robotic manipulation is difficult due to the challenges of simulating complex contacts and generating realistic task distributions. To tackle the latter problem, we introduce ManipGen, which leverages a new class of policies for sim2real transfer: local policies. Locality enables a variety of appealing properties including invariances to absolute robot and object pose, skill ordering, and global scene configuration. We combine these policies with foundation models for vision, language and motion planning and demonstrate SOTA zero-shot performance of our method to Robosuite benchma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22332","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/2410.22332/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":"2410.22332","created_at":"2026-07-05T10:27:18.457000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22332v2","created_at":"2026-07-05T10:27:18.457000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22332","created_at":"2026-07-05T10:27:18.457000+00:00"},{"alias_kind":"pith_short_12","alias_value":"MROC5BMTXKCP","created_at":"2026-07-05T10:27:18.457000+00:00"},{"alias_kind":"pith_short_16","alias_value":"MROC5BMTXKCPMRFK","created_at":"2026-07-05T10:27:18.457000+00:00"},{"alias_kind":"pith_short_8","alias_value":"MROC5BMT","created_at":"2026-07-05T10:27:18.457000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20085","citing_title":"HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MROC5BMTXKCPMRFKJLPDOQDHQG","json":"https://pith.science/pith/MROC5BMTXKCPMRFKJLPDOQDHQG.json","graph_json":"https://pith.science/api/pith-number/MROC5BMTXKCPMRFKJLPDOQDHQG/graph.json","events_json":"https://pith.science/api/pith-number/MROC5BMTXKCPMRFKJLPDOQDHQG/events.json","paper":"https://pith.science/paper/MROC5BMT"},"agent_actions":{"view_html":"https://pith.science/pith/MROC5BMTXKCPMRFKJLPDOQDHQG","download_json":"https://pith.science/pith/MROC5BMTXKCPMRFKJLPDOQDHQG.json","view_paper":"https://pith.science/paper/MROC5BMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22332&json=true","fetch_graph":"https://pith.science/api/pith-number/MROC5BMTXKCPMRFKJLPDOQDHQG/graph.json","fetch_events":"https://pith.science/api/pith-number/MROC5BMTXKCPMRFKJLPDOQDHQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MROC5BMTXKCPMRFKJLPDOQDHQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MROC5BMTXKCPMRFKJLPDOQDHQG/action/storage_attestation","attest_author":"https://pith.science/pith/MROC5BMTXKCPMRFKJLPDOQDHQG/action/author_attestation","sign_citation":"https://pith.science/pith/MROC5BMTXKCPMRFKJLPDOQDHQG/action/citation_signature","submit_replication":"https://pith.science/pith/MROC5BMTXKCPMRFKJLPDOQDHQG/action/replication_record"}},"created_at":"2026-07-05T10:27:18.457000+00:00","updated_at":"2026-07-05T10:27:18.457000+00:00"}