{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:DTLUCURVOUV7ZJOTCR2FR6BYUJ","short_pith_number":"pith:DTLUCURV","schema_version":"1.0","canonical_sha256":"1cd7415235752bfca5d3147458f838a267b8ef47a219b62ee176320dc52f800b","source":{"kind":"arxiv","id":"1511.07727","version":2},"attestation_state":"computed","paper":{"title":"DiffSharp: Automatic Differentiation Library","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MS","authors_text":"Atilim Gunes Baydin, Barak A. Pearlmutter, Jeffrey Mark Siskind","submitted_at":"2015-11-24T14:28:13Z","abstract_excerpt":"In this paper we introduce DiffSharp, an automatic differentiation (AD) library designed with machine learning in mind. AD is a family of techniques that evaluate derivatives at machine precision with only a small constant factor of overhead, by systematically applying the chain rule of calculus at the elementary operator level. DiffSharp aims to make an extensive array of AD techniques available, in convenient form, to the machine learning community. These including arbitrary nesting of forward/reverse AD operations, AD with linear algebra primitives, and a functional API that emphasizes the "},"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":"1511.07727","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MS","submitted_at":"2015-11-24T14:28:13Z","cross_cats_sorted":[],"title_canon_sha256":"1912528b864a35367d8eb4ab62185e5e380dbc35534dab98e044bd98d7278a36","abstract_canon_sha256":"2350ea145fa6bf5574be11f6a051490801474ef2c55d7205e94e0958dbce4674"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:54.590751Z","signature_b64":"AKCHOc7vwjMSMErOkt+8U9xqhzf3a5SC+X8dOcpZ7cyW91ncu6x/0KIGidWw13iDvhSvRYe8MYZRIzObhdNNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cd7415235752bfca5d3147458f838a267b8ef47a219b62ee176320dc52f800b","last_reissued_at":"2026-05-18T01:25:54.590069Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:54.590069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffSharp: Automatic Differentiation Library","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MS","authors_text":"Atilim Gunes Baydin, Barak A. Pearlmutter, Jeffrey Mark Siskind","submitted_at":"2015-11-24T14:28:13Z","abstract_excerpt":"In this paper we introduce DiffSharp, an automatic differentiation (AD) library designed with machine learning in mind. AD is a family of techniques that evaluate derivatives at machine precision with only a small constant factor of overhead, by systematically applying the chain rule of calculus at the elementary operator level. DiffSharp aims to make an extensive array of AD techniques available, in convenient form, to the machine learning community. These including arbitrary nesting of forward/reverse AD operations, AD with linear algebra primitives, and a functional API that emphasizes the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07727","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":""},"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":"1511.07727","created_at":"2026-05-18T01:25:54.590166+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.07727v2","created_at":"2026-05-18T01:25:54.590166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07727","created_at":"2026-05-18T01:25:54.590166+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTLUCURVOUV7","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTLUCURVOUV7ZJOT","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTLUCURV","created_at":"2026-05-18T12:29:17.054201+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/DTLUCURVOUV7ZJOTCR2FR6BYUJ","json":"https://pith.science/pith/DTLUCURVOUV7ZJOTCR2FR6BYUJ.json","graph_json":"https://pith.science/api/pith-number/DTLUCURVOUV7ZJOTCR2FR6BYUJ/graph.json","events_json":"https://pith.science/api/pith-number/DTLUCURVOUV7ZJOTCR2FR6BYUJ/events.json","paper":"https://pith.science/paper/DTLUCURV"},"agent_actions":{"view_html":"https://pith.science/pith/DTLUCURVOUV7ZJOTCR2FR6BYUJ","download_json":"https://pith.science/pith/DTLUCURVOUV7ZJOTCR2FR6BYUJ.json","view_paper":"https://pith.science/paper/DTLUCURV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.07727&json=true","fetch_graph":"https://pith.science/api/pith-number/DTLUCURVOUV7ZJOTCR2FR6BYUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DTLUCURVOUV7ZJOTCR2FR6BYUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTLUCURVOUV7ZJOTCR2FR6BYUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTLUCURVOUV7ZJOTCR2FR6BYUJ/action/storage_attestation","attest_author":"https://pith.science/pith/DTLUCURVOUV7ZJOTCR2FR6BYUJ/action/author_attestation","sign_citation":"https://pith.science/pith/DTLUCURVOUV7ZJOTCR2FR6BYUJ/action/citation_signature","submit_replication":"https://pith.science/pith/DTLUCURVOUV7ZJOTCR2FR6BYUJ/action/replication_record"}},"created_at":"2026-05-18T01:25:54.590166+00:00","updated_at":"2026-05-18T01:25:54.590166+00:00"}