{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GA6ZK5XWWQWG6GRCPVPAEAI2P6","short_pith_number":"pith:GA6ZK5XW","schema_version":"1.0","canonical_sha256":"303d9576f6b42c6f1a227d5e02011a7fbfc1241b694913a235133a1a36ac149d","source":{"kind":"arxiv","id":"2209.10021","version":3},"attestation_state":"computed","paper":{"title":"DiffTune: Auto-Tuning through Auto-Differentiation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chengyu Yang, Lin Song, Minkyung Kim, Naira Hovakimyan, Sheng Cheng, Shenlong Wang, Yiquan Jin","submitted_at":"2022-09-20T22:08:44Z","abstract_excerpt":"The performance of robots in high-level tasks depends on the quality of their lower-level controller, which requires fine-tuning. However, the intrinsically nonlinear dynamics and controllers make tuning a challenging task when it is done by hand. In this paper, we present DiffTune, a novel, gradient-based automatic tuning framework. We formulate the controller tuning as a parameter optimization problem. Our method unrolls the dynamical system and controller as a computational graph and updates the controller parameters through gradient-based optimization. The gradient is obtained using sensit"},"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":"2209.10021","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-20T22:08:44Z","cross_cats_sorted":[],"title_canon_sha256":"eb877fa82ec88653af4c010dbb7550bd892d69a8fad667a4fc1766c27483bfaa","abstract_canon_sha256":"b5ec124ccf3545807a340e2c37bee551dea77d37aad28f43c277babfa7d4fbad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:28.251356Z","signature_b64":"QRB/yAGt1rFgN5fiDtyae8LGOmNpF43eiejvmDrb1xOWJFkjZyLxed1lyvEPMqBGl9QvtKbj8EwYfW1Eueu7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"303d9576f6b42c6f1a227d5e02011a7fbfc1241b694913a235133a1a36ac149d","last_reissued_at":"2026-07-05T08:42:28.250907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:28.250907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffTune: Auto-Tuning through Auto-Differentiation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chengyu Yang, Lin Song, Minkyung Kim, Naira Hovakimyan, Sheng Cheng, Shenlong Wang, Yiquan Jin","submitted_at":"2022-09-20T22:08:44Z","abstract_excerpt":"The performance of robots in high-level tasks depends on the quality of their lower-level controller, which requires fine-tuning. However, the intrinsically nonlinear dynamics and controllers make tuning a challenging task when it is done by hand. In this paper, we present DiffTune, a novel, gradient-based automatic tuning framework. We formulate the controller tuning as a parameter optimization problem. Our method unrolls the dynamical system and controller as a computational graph and updates the controller parameters through gradient-based optimization. The gradient is obtained using sensit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10021","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/2209.10021/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":"2209.10021","created_at":"2026-07-05T08:42:28.250964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10021v3","created_at":"2026-07-05T08:42:28.250964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10021","created_at":"2026-07-05T08:42:28.250964+00:00"},{"alias_kind":"pith_short_12","alias_value":"GA6ZK5XWWQWG","created_at":"2026-07-05T08:42:28.250964+00:00"},{"alias_kind":"pith_short_16","alias_value":"GA6ZK5XWWQWG6GRC","created_at":"2026-07-05T08:42:28.250964+00:00"},{"alias_kind":"pith_short_8","alias_value":"GA6ZK5XW","created_at":"2026-07-05T08:42:28.250964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GA6ZK5XWWQWG6GRCPVPAEAI2P6","json":"https://pith.science/pith/GA6ZK5XWWQWG6GRCPVPAEAI2P6.json","graph_json":"https://pith.science/api/pith-number/GA6ZK5XWWQWG6GRCPVPAEAI2P6/graph.json","events_json":"https://pith.science/api/pith-number/GA6ZK5XWWQWG6GRCPVPAEAI2P6/events.json","paper":"https://pith.science/paper/GA6ZK5XW"},"agent_actions":{"view_html":"https://pith.science/pith/GA6ZK5XWWQWG6GRCPVPAEAI2P6","download_json":"https://pith.science/pith/GA6ZK5XWWQWG6GRCPVPAEAI2P6.json","view_paper":"https://pith.science/paper/GA6ZK5XW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10021&json=true","fetch_graph":"https://pith.science/api/pith-number/GA6ZK5XWWQWG6GRCPVPAEAI2P6/graph.json","fetch_events":"https://pith.science/api/pith-number/GA6ZK5XWWQWG6GRCPVPAEAI2P6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GA6ZK5XWWQWG6GRCPVPAEAI2P6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GA6ZK5XWWQWG6GRCPVPAEAI2P6/action/storage_attestation","attest_author":"https://pith.science/pith/GA6ZK5XWWQWG6GRCPVPAEAI2P6/action/author_attestation","sign_citation":"https://pith.science/pith/GA6ZK5XWWQWG6GRCPVPAEAI2P6/action/citation_signature","submit_replication":"https://pith.science/pith/GA6ZK5XWWQWG6GRCPVPAEAI2P6/action/replication_record"}},"created_at":"2026-07-05T08:42:28.250964+00:00","updated_at":"2026-07-05T08:42:28.250964+00:00"}