{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:U4WYCN76E5K6YGZXHBPD7F2HWE","short_pith_number":"pith:U4WYCN76","schema_version":"1.0","canonical_sha256":"a72d8137fe2755ec1b37385e3f9747b1108590a249c2a19c673d56ac8908cb02","source":{"kind":"arxiv","id":"2001.00706","version":2},"attestation_state":"computed","paper":{"title":"Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Patrick Kidger, Terry Lyons","submitted_at":"2020-01-03T03:15:58Z","abstract_excerpt":"Signatory is a library for calculating and performing functionality related to the signature and logsignature transforms. The focus is on machine learning, and as such includes features such as CPU parallelism, GPU support, and backpropagation. To our knowledge it is the first GPU-capable library for these operations. Signatory implements new features not available in previous libraries, such as efficient precomputation strategies. Furthermore, several novel algorithmic improvements are introduced, producing substantial real-world speedups even on the CPU without parallelism. The library opera"},"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":"2001.00706","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-03T03:15:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"42db7ae6f9fc02386da94dded2889b0dd52db7eda30563e4ddc7c919f874f6ae","abstract_canon_sha256":"1844146c8a8d2065489e7d5e020b684ab2d22694a9d47f1ffdfde7cc724f2c23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:12.384797Z","signature_b64":"m698I0vOsNiwIqSWYu4fJREgQODWbeQq0TUYuNdEP93W+/vpRswWUzV9CI28pn6CmDM8V6bsLdZhezWIZQUYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a72d8137fe2755ec1b37385e3f9747b1108590a249c2a19c673d56ac8908cb02","last_reissued_at":"2026-07-05T02:13:12.384364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:12.384364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Patrick Kidger, Terry Lyons","submitted_at":"2020-01-03T03:15:58Z","abstract_excerpt":"Signatory is a library for calculating and performing functionality related to the signature and logsignature transforms. The focus is on machine learning, and as such includes features such as CPU parallelism, GPU support, and backpropagation. To our knowledge it is the first GPU-capable library for these operations. Signatory implements new features not available in previous libraries, such as efficient precomputation strategies. Furthermore, several novel algorithmic improvements are introduced, producing substantial real-world speedups even on the CPU without parallelism. The library opera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00706","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/2001.00706/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":"2001.00706","created_at":"2026-07-05T02:13:12.384430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.00706v2","created_at":"2026-07-05T02:13:12.384430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00706","created_at":"2026-07-05T02:13:12.384430+00:00"},{"alias_kind":"pith_short_12","alias_value":"U4WYCN76E5K6","created_at":"2026-07-05T02:13:12.384430+00:00"},{"alias_kind":"pith_short_16","alias_value":"U4WYCN76E5K6YGZX","created_at":"2026-07-05T02:13:12.384430+00:00"},{"alias_kind":"pith_short_8","alias_value":"U4WYCN76","created_at":"2026-07-05T02:13:12.384430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.14551","citing_title":"TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U4WYCN76E5K6YGZXHBPD7F2HWE","json":"https://pith.science/pith/U4WYCN76E5K6YGZXHBPD7F2HWE.json","graph_json":"https://pith.science/api/pith-number/U4WYCN76E5K6YGZXHBPD7F2HWE/graph.json","events_json":"https://pith.science/api/pith-number/U4WYCN76E5K6YGZXHBPD7F2HWE/events.json","paper":"https://pith.science/paper/U4WYCN76"},"agent_actions":{"view_html":"https://pith.science/pith/U4WYCN76E5K6YGZXHBPD7F2HWE","download_json":"https://pith.science/pith/U4WYCN76E5K6YGZXHBPD7F2HWE.json","view_paper":"https://pith.science/paper/U4WYCN76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.00706&json=true","fetch_graph":"https://pith.science/api/pith-number/U4WYCN76E5K6YGZXHBPD7F2HWE/graph.json","fetch_events":"https://pith.science/api/pith-number/U4WYCN76E5K6YGZXHBPD7F2HWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U4WYCN76E5K6YGZXHBPD7F2HWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U4WYCN76E5K6YGZXHBPD7F2HWE/action/storage_attestation","attest_author":"https://pith.science/pith/U4WYCN76E5K6YGZXHBPD7F2HWE/action/author_attestation","sign_citation":"https://pith.science/pith/U4WYCN76E5K6YGZXHBPD7F2HWE/action/citation_signature","submit_replication":"https://pith.science/pith/U4WYCN76E5K6YGZXHBPD7F2HWE/action/replication_record"}},"created_at":"2026-07-05T02:13:12.384430+00:00","updated_at":"2026-07-05T02:13:12.384430+00:00"}