{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NMV4AURBDDYLSIN5LBTT4U5Q3D","short_pith_number":"pith:NMV4AURB","schema_version":"1.0","canonical_sha256":"6b2bc0522118f0b921bd58673e53b0d8ce1f282ca9c91cec018d1d696d95cc8b","source":{"kind":"arxiv","id":"2207.09442","version":3},"attestation_state":"computed","paper":{"title":"Theseus: A Library for Differentiable Nonlinear Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","math.OC"],"primary_cat":"cs.RO","authors_text":"Austin Wang, Brandon Amos, Daniel DeTone, Jing Dong, Joseph Ortiz, Luis Pineda, Maurizio Monge, Mustafa Mukadam, Paloma Sodhi, Ricky T. Q. Chen, Shobha Venkataraman, Stuart Anderson, Taosha Fan","submitted_at":"2022-07-19T17:57:40Z","abstract_excerpt":"We present Theseus, an efficient application-agnostic open source library for differentiable nonlinear least squares (DNLS) optimization built on PyTorch, providing a common framework for end-to-end structured learning in robotics and vision. Existing DNLS implementations are application specific and do not always incorporate many ingredients important for efficiency. Theseus is application-agnostic, as we illustrate with several example applications that are built using the same underlying differentiable components, such as second-order optimizers, standard costs functions, and Lie groups. Fo"},"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":"2207.09442","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-07-19T17:57:40Z","cross_cats_sorted":["cs.CV","cs.LG","math.OC"],"title_canon_sha256":"674357dc4f26ffffdb346c6fe91a161c0dadf459549d15bab5cefe1852056821","abstract_canon_sha256":"b02938d9744367824913daa04aba73453ba8777b4b2713369d5adc3740d68b39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:01.993743Z","signature_b64":"uAQ33EYAStcJopJWbpIenNYyHNNwz5ZrmA6/dXPCiJmtOPFuUjBUl3aYLteDAftRKWYtZP5ybyM8wv3B4gYvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b2bc0522118f0b921bd58673e53b0d8ce1f282ca9c91cec018d1d696d95cc8b","last_reissued_at":"2026-07-05T05:34:01.993276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:01.993276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theseus: A Library for Differentiable Nonlinear Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","math.OC"],"primary_cat":"cs.RO","authors_text":"Austin Wang, Brandon Amos, Daniel DeTone, Jing Dong, Joseph Ortiz, Luis Pineda, Maurizio Monge, Mustafa Mukadam, Paloma Sodhi, Ricky T. Q. Chen, Shobha Venkataraman, Stuart Anderson, Taosha Fan","submitted_at":"2022-07-19T17:57:40Z","abstract_excerpt":"We present Theseus, an efficient application-agnostic open source library for differentiable nonlinear least squares (DNLS) optimization built on PyTorch, providing a common framework for end-to-end structured learning in robotics and vision. Existing DNLS implementations are application specific and do not always incorporate many ingredients important for efficiency. Theseus is application-agnostic, as we illustrate with several example applications that are built using the same underlying differentiable components, such as second-order optimizers, standard costs functions, and Lie groups. Fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09442","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/2207.09442/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":"2207.09442","created_at":"2026-07-05T05:34:01.993341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.09442v3","created_at":"2026-07-05T05:34:01.993341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09442","created_at":"2026-07-05T05:34:01.993341+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMV4AURBDDYL","created_at":"2026-07-05T05:34:01.993341+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMV4AURBDDYLSIN5","created_at":"2026-07-05T05:34:01.993341+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMV4AURB","created_at":"2026-07-05T05:34:01.993341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.28886","citing_title":"Differentiable Approximations for Distance Queries","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NMV4AURBDDYLSIN5LBTT4U5Q3D","json":"https://pith.science/pith/NMV4AURBDDYLSIN5LBTT4U5Q3D.json","graph_json":"https://pith.science/api/pith-number/NMV4AURBDDYLSIN5LBTT4U5Q3D/graph.json","events_json":"https://pith.science/api/pith-number/NMV4AURBDDYLSIN5LBTT4U5Q3D/events.json","paper":"https://pith.science/paper/NMV4AURB"},"agent_actions":{"view_html":"https://pith.science/pith/NMV4AURBDDYLSIN5LBTT4U5Q3D","download_json":"https://pith.science/pith/NMV4AURBDDYLSIN5LBTT4U5Q3D.json","view_paper":"https://pith.science/paper/NMV4AURB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.09442&json=true","fetch_graph":"https://pith.science/api/pith-number/NMV4AURBDDYLSIN5LBTT4U5Q3D/graph.json","fetch_events":"https://pith.science/api/pith-number/NMV4AURBDDYLSIN5LBTT4U5Q3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMV4AURBDDYLSIN5LBTT4U5Q3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMV4AURBDDYLSIN5LBTT4U5Q3D/action/storage_attestation","attest_author":"https://pith.science/pith/NMV4AURBDDYLSIN5LBTT4U5Q3D/action/author_attestation","sign_citation":"https://pith.science/pith/NMV4AURBDDYLSIN5LBTT4U5Q3D/action/citation_signature","submit_replication":"https://pith.science/pith/NMV4AURBDDYLSIN5LBTT4U5Q3D/action/replication_record"}},"created_at":"2026-07-05T05:34:01.993341+00:00","updated_at":"2026-07-05T05:34:01.993341+00:00"}