{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OX5C6TJD4BUUWOUDVEMYJNRPIL","short_pith_number":"pith:OX5C6TJD","schema_version":"1.0","canonical_sha256":"75fa2f4d23e0694b3a83a91984b62f42ccad657697b08cf232658156fd04b055","source":{"kind":"arxiv","id":"2110.03659","version":3},"attestation_state":"computed","paper":{"title":"Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","cs.RO"],"primary_cat":"cs.LG","authors_text":"Kris Kitani, Wen Sun, Ye Yuan, Yuda Song, Zhengyi Luo","submitted_at":"2021-10-07T17:51:05Z","abstract_excerpt":"An agent's functionality is largely determined by its design, i.e., skeletal structure and joint attributes (e.g., length, size, strength). However, finding the optimal agent design for a given function is extremely challenging since the problem is inherently combinatorial and the design space is prohibitively large. Additionally, it can be costly to evaluate each candidate design which requires solving for its optimal controller. To tackle these problems, our key idea is to incorporate the design procedure of an agent into its decision-making process. Specifically, we learn a conditional poli"},"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":"2110.03659","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T17:51:05Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","cs.RO"],"title_canon_sha256":"73e8b97762d029626a9cee8a97b414e1a6eda1a40939bebe3be7ae7dee916d14","abstract_canon_sha256":"a1d13f4105d09dde63ec1d2a1cd402826f998b1c347b64814fa0f5b6c18f46fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:50.825864Z","signature_b64":"4JV9Zii3RWmlgvIwX4zm6fbzTSDGb9Cfd3sQCvgGf+evCVQfvrgZvMKOnQ5IDKAkDmoGzrMa7NmMrDj61XWEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75fa2f4d23e0694b3a83a91984b62f42ccad657697b08cf232658156fd04b055","last_reissued_at":"2026-07-05T04:12:50.825412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:50.825412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","cs.RO"],"primary_cat":"cs.LG","authors_text":"Kris Kitani, Wen Sun, Ye Yuan, Yuda Song, Zhengyi Luo","submitted_at":"2021-10-07T17:51:05Z","abstract_excerpt":"An agent's functionality is largely determined by its design, i.e., skeletal structure and joint attributes (e.g., length, size, strength). However, finding the optimal agent design for a given function is extremely challenging since the problem is inherently combinatorial and the design space is prohibitively large. Additionally, it can be costly to evaluate each candidate design which requires solving for its optimal controller. To tackle these problems, our key idea is to incorporate the design procedure of an agent into its decision-making process. Specifically, we learn a conditional poli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03659","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/2110.03659/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":"2110.03659","created_at":"2026-07-05T04:12:50.825484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03659v3","created_at":"2026-07-05T04:12:50.825484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03659","created_at":"2026-07-05T04:12:50.825484+00:00"},{"alias_kind":"pith_short_12","alias_value":"OX5C6TJD4BUU","created_at":"2026-07-05T04:12:50.825484+00:00"},{"alias_kind":"pith_short_16","alias_value":"OX5C6TJD4BUUWOUD","created_at":"2026-07-05T04:12:50.825484+00:00"},{"alias_kind":"pith_short_8","alias_value":"OX5C6TJD","created_at":"2026-07-05T04:12:50.825484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07424","citing_title":"Rapid co-design of Buoyancy-assisted robots for Challenging Locomotion using Gaussian Evolutionary Specialists","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25832","citing_title":"When Search Becomes Memory: Turning Robot Design Trials into Transferable Skills","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00702","citing_title":"Shape Your Body: Value Gradients for Multi-Embodiment Robot Design","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03743","citing_title":"House of Dextra: Cross-embodied Co-design for Dexterous Hands","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OX5C6TJD4BUUWOUDVEMYJNRPIL","json":"https://pith.science/pith/OX5C6TJD4BUUWOUDVEMYJNRPIL.json","graph_json":"https://pith.science/api/pith-number/OX5C6TJD4BUUWOUDVEMYJNRPIL/graph.json","events_json":"https://pith.science/api/pith-number/OX5C6TJD4BUUWOUDVEMYJNRPIL/events.json","paper":"https://pith.science/paper/OX5C6TJD"},"agent_actions":{"view_html":"https://pith.science/pith/OX5C6TJD4BUUWOUDVEMYJNRPIL","download_json":"https://pith.science/pith/OX5C6TJD4BUUWOUDVEMYJNRPIL.json","view_paper":"https://pith.science/paper/OX5C6TJD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03659&json=true","fetch_graph":"https://pith.science/api/pith-number/OX5C6TJD4BUUWOUDVEMYJNRPIL/graph.json","fetch_events":"https://pith.science/api/pith-number/OX5C6TJD4BUUWOUDVEMYJNRPIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OX5C6TJD4BUUWOUDVEMYJNRPIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OX5C6TJD4BUUWOUDVEMYJNRPIL/action/storage_attestation","attest_author":"https://pith.science/pith/OX5C6TJD4BUUWOUDVEMYJNRPIL/action/author_attestation","sign_citation":"https://pith.science/pith/OX5C6TJD4BUUWOUDVEMYJNRPIL/action/citation_signature","submit_replication":"https://pith.science/pith/OX5C6TJD4BUUWOUDVEMYJNRPIL/action/replication_record"}},"created_at":"2026-07-05T04:12:50.825484+00:00","updated_at":"2026-07-05T04:12:50.825484+00:00"}