{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RLR5XZFNSUT3W7QBQXEHPNZJQ6","short_pith_number":"pith:RLR5XZFN","schema_version":"1.0","canonical_sha256":"8ae3dbe4ad9527bb7e0185c877b72987bf91ed0f0e3b9253bb8a1140414ae0db","source":{"kind":"arxiv","id":"1912.08168","version":2},"attestation_state":"computed","paper":{"title":"Differentiable programming and its applications to dynamical systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"math.DS","authors_text":"Adri\\'an Hern\\'andez, Jos\\'e M. Amig\\'o","submitted_at":"2019-12-17T18:12:06Z","abstract_excerpt":"Differentiable programming is the combination of classical neural networks modules with algorithmic ones in an end-to-end differentiable model. These new models, that use automatic differentiation to calculate gradients, have new learning capabilities (reasoning, attention and memory). In this tutorial, aimed at researchers in nonlinear systems with prior knowledge of deep learning, we present this new programming paradigm, describe some of its new features such as attention mechanisms, and highlight the benefits they bring. Then, we analyse the uses and limitations of traditional deep learnin"},"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":"1912.08168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.DS","submitted_at":"2019-12-17T18:12:06Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"0ac0c2a69a82ac85f54ee00e3d674164effbad9de240fe3663bc4d2dce1cbf15","abstract_canon_sha256":"d3540b262ab9c5468cc918079d5464cf88029f501f0dab139cd69c07220daa02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:56.120974Z","signature_b64":"zPWbaYrSyOU9SmzRsMf67eDv/L8wZ2tzCTk8S2ueuOKNERZyQw3kkd7og1+zakrFow7TEpE8vPAdzMY94DuODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ae3dbe4ad9527bb7e0185c877b72987bf91ed0f0e3b9253bb8a1140414ae0db","last_reissued_at":"2026-07-05T00:59:56.120559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:56.120559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable programming and its applications to dynamical systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"math.DS","authors_text":"Adri\\'an Hern\\'andez, Jos\\'e M. Amig\\'o","submitted_at":"2019-12-17T18:12:06Z","abstract_excerpt":"Differentiable programming is the combination of classical neural networks modules with algorithmic ones in an end-to-end differentiable model. These new models, that use automatic differentiation to calculate gradients, have new learning capabilities (reasoning, attention and memory). In this tutorial, aimed at researchers in nonlinear systems with prior knowledge of deep learning, we present this new programming paradigm, describe some of its new features such as attention mechanisms, and highlight the benefits they bring. Then, we analyse the uses and limitations of traditional deep learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.08168","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/1912.08168/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":"1912.08168","created_at":"2026-07-05T00:59:56.120615+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.08168v2","created_at":"2026-07-05T00:59:56.120615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.08168","created_at":"2026-07-05T00:59:56.120615+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLR5XZFNSUT3","created_at":"2026-07-05T00:59:56.120615+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLR5XZFNSUT3W7QB","created_at":"2026-07-05T00:59:56.120615+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLR5XZFN","created_at":"2026-07-05T00:59:56.120615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06094","citing_title":"Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLR5XZFNSUT3W7QBQXEHPNZJQ6","json":"https://pith.science/pith/RLR5XZFNSUT3W7QBQXEHPNZJQ6.json","graph_json":"https://pith.science/api/pith-number/RLR5XZFNSUT3W7QBQXEHPNZJQ6/graph.json","events_json":"https://pith.science/api/pith-number/RLR5XZFNSUT3W7QBQXEHPNZJQ6/events.json","paper":"https://pith.science/paper/RLR5XZFN"},"agent_actions":{"view_html":"https://pith.science/pith/RLR5XZFNSUT3W7QBQXEHPNZJQ6","download_json":"https://pith.science/pith/RLR5XZFNSUT3W7QBQXEHPNZJQ6.json","view_paper":"https://pith.science/paper/RLR5XZFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.08168&json=true","fetch_graph":"https://pith.science/api/pith-number/RLR5XZFNSUT3W7QBQXEHPNZJQ6/graph.json","fetch_events":"https://pith.science/api/pith-number/RLR5XZFNSUT3W7QBQXEHPNZJQ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLR5XZFNSUT3W7QBQXEHPNZJQ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLR5XZFNSUT3W7QBQXEHPNZJQ6/action/storage_attestation","attest_author":"https://pith.science/pith/RLR5XZFNSUT3W7QBQXEHPNZJQ6/action/author_attestation","sign_citation":"https://pith.science/pith/RLR5XZFNSUT3W7QBQXEHPNZJQ6/action/citation_signature","submit_replication":"https://pith.science/pith/RLR5XZFNSUT3W7QBQXEHPNZJQ6/action/replication_record"}},"created_at":"2026-07-05T00:59:56.120615+00:00","updated_at":"2026-07-05T00:59:56.120615+00:00"}