{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OKY3APLM2WHDTYIVQGJ77VHM25","short_pith_number":"pith:OKY3APLM","schema_version":"1.0","canonical_sha256":"72b1b03d6cd58e39e1158193ffd4ecd74133b716ebfd9bbc7765e0faae7c37b8","source":{"kind":"arxiv","id":"2203.13733","version":2},"attestation_state":"computed","paper":{"title":"Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Byron David, Daniel Freeman, Igor Mordatch, Satoshi Kataoka, Seyed Kamyar Seyed Ghasemipour, Shixiang Shane Gu","submitted_at":"2022-03-15T18:21:02Z","abstract_excerpt":"Assembly of multi-part physical structures is both a valuable end product for autonomous robotics, as well as a valuable diagnostic task for open-ended training of embodied intelligent agents. We introduce a naturalistic physics-based environment with a set of connectable magnet blocks inspired by children's toy kits. The objective is to assemble blocks into a succession of target blueprints. Despite the simplicity of this objective, the compositional nature of building diverse blueprints from a set of blocks leads to an explosion of complexity in structures that agents encounter. Furthermore,"},"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":"2203.13733","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-15T18:21:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ddfefafd49e7a978b55ffa15da2df80e17e6fc314f9ec3515e3f085565113d11","abstract_canon_sha256":"ce342ee94ca1108a3acb7711c554a93aec47794707ee60b05e8182d79cfe761e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:55.019407Z","signature_b64":"kz1uc14rQG1e/YjIMsRBkXKJZGicP+BorOjwS37JKiy4lUHt7is2IHLhdVKtGBOiVsexEkRA+xRxprlww3YIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72b1b03d6cd58e39e1158193ffd4ecd74133b716ebfd9bbc7765e0faae7c37b8","last_reissued_at":"2026-07-05T04:13:55.018916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:55.018916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Byron David, Daniel Freeman, Igor Mordatch, Satoshi Kataoka, Seyed Kamyar Seyed Ghasemipour, Shixiang Shane Gu","submitted_at":"2022-03-15T18:21:02Z","abstract_excerpt":"Assembly of multi-part physical structures is both a valuable end product for autonomous robotics, as well as a valuable diagnostic task for open-ended training of embodied intelligent agents. We introduce a naturalistic physics-based environment with a set of connectable magnet blocks inspired by children's toy kits. The objective is to assemble blocks into a succession of target blueprints. Despite the simplicity of this objective, the compositional nature of building diverse blueprints from a set of blocks leads to an explosion of complexity in structures that agents encounter. Furthermore,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13733","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/2203.13733/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":"2203.13733","created_at":"2026-07-05T04:13:55.018978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.13733v2","created_at":"2026-07-05T04:13:55.018978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13733","created_at":"2026-07-05T04:13:55.018978+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKY3APLM2WHD","created_at":"2026-07-05T04:13:55.018978+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKY3APLM2WHDTYIV","created_at":"2026-07-05T04:13:55.018978+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKY3APLM","created_at":"2026-07-05T04:13:55.018978+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18872","citing_title":"EUPHORIA: Efficient Universal Planning via Hybrid Optimization for Robust Industrial Robotic Assembly","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKY3APLM2WHDTYIVQGJ77VHM25","json":"https://pith.science/pith/OKY3APLM2WHDTYIVQGJ77VHM25.json","graph_json":"https://pith.science/api/pith-number/OKY3APLM2WHDTYIVQGJ77VHM25/graph.json","events_json":"https://pith.science/api/pith-number/OKY3APLM2WHDTYIVQGJ77VHM25/events.json","paper":"https://pith.science/paper/OKY3APLM"},"agent_actions":{"view_html":"https://pith.science/pith/OKY3APLM2WHDTYIVQGJ77VHM25","download_json":"https://pith.science/pith/OKY3APLM2WHDTYIVQGJ77VHM25.json","view_paper":"https://pith.science/paper/OKY3APLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.13733&json=true","fetch_graph":"https://pith.science/api/pith-number/OKY3APLM2WHDTYIVQGJ77VHM25/graph.json","fetch_events":"https://pith.science/api/pith-number/OKY3APLM2WHDTYIVQGJ77VHM25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKY3APLM2WHDTYIVQGJ77VHM25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKY3APLM2WHDTYIVQGJ77VHM25/action/storage_attestation","attest_author":"https://pith.science/pith/OKY3APLM2WHDTYIVQGJ77VHM25/action/author_attestation","sign_citation":"https://pith.science/pith/OKY3APLM2WHDTYIVQGJ77VHM25/action/citation_signature","submit_replication":"https://pith.science/pith/OKY3APLM2WHDTYIVQGJ77VHM25/action/replication_record"}},"created_at":"2026-07-05T04:13:55.018978+00:00","updated_at":"2026-07-05T04:13:55.018978+00:00"}