{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NNL4WTDN4NY3U2K4INDPWSMIFC","short_pith_number":"pith:NNL4WTDN","schema_version":"1.0","canonical_sha256":"6b57cb4c6de371ba695c4346fb498828acd8e8240d59de38fdc1594c59229c36","source":{"kind":"arxiv","id":"1706.04859","version":3},"attestation_state":"computed","paper":{"title":"Sobolev Training for Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Grzegorz \\'Swirszcz, Max Jaderberg, Razvan Pascanu, Simon Osindero, Wojciech Marian Czarnecki","submitted_at":"2017-06-15T13:25:25Z","abstract_excerpt":"At the heart of deep learning we aim to use neural networks as function approximators - training them to produce outputs from inputs in emulation of a ground truth function or data creation process. In many cases we only have access to input-output pairs from the ground truth, however it is becoming more common to have access to derivatives of the target output with respect to the input - for example when the ground truth function is itself a neural network such as in network compression or distillation. Generally these target derivatives are not computed, or are ignored. This paper introduces"},"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":"1706.04859","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-15T13:25:25Z","cross_cats_sorted":[],"title_canon_sha256":"c35d551a78657521098a42baea27e900bc8969b01d6ec144b997c148b676c511","abstract_canon_sha256":"553ac0d90a853a88d0c003b60f2a182d4370c34ec7eae07a0301df597d962a4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:25.571536Z","signature_b64":"dIgQ0vvGTIjyF5Icufeo7NxXEA571+h11c8zcclt8b3ezoNqapMVOlTz6PpGroYx71ad+j/7HR+jlGuYuv+6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b57cb4c6de371ba695c4346fb498828acd8e8240d59de38fdc1594c59229c36","last_reissued_at":"2026-05-18T00:39:25.571031Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:25.571031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sobolev Training for Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Grzegorz \\'Swirszcz, Max Jaderberg, Razvan Pascanu, Simon Osindero, Wojciech Marian Czarnecki","submitted_at":"2017-06-15T13:25:25Z","abstract_excerpt":"At the heart of deep learning we aim to use neural networks as function approximators - training them to produce outputs from inputs in emulation of a ground truth function or data creation process. In many cases we only have access to input-output pairs from the ground truth, however it is becoming more common to have access to derivatives of the target output with respect to the input - for example when the ground truth function is itself a neural network such as in network compression or distillation. Generally these target derivatives are not computed, or are ignored. This paper introduces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04859","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":""},"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":"1706.04859","created_at":"2026-05-18T00:39:25.571100+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.04859v3","created_at":"2026-05-18T00:39:25.571100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04859","created_at":"2026-05-18T00:39:25.571100+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNL4WTDN4NY3","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNL4WTDN4NY3U2K4","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNL4WTDN","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.15463","citing_title":"Layer-wise Derivative Controlled Networks","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14939","citing_title":"Real-time virtual circuits for plasma shape control via neural network emulators","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02190","citing_title":"KANs need curvature: penalties for compositional smoothness","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNL4WTDN4NY3U2K4INDPWSMIFC","json":"https://pith.science/pith/NNL4WTDN4NY3U2K4INDPWSMIFC.json","graph_json":"https://pith.science/api/pith-number/NNL4WTDN4NY3U2K4INDPWSMIFC/graph.json","events_json":"https://pith.science/api/pith-number/NNL4WTDN4NY3U2K4INDPWSMIFC/events.json","paper":"https://pith.science/paper/NNL4WTDN"},"agent_actions":{"view_html":"https://pith.science/pith/NNL4WTDN4NY3U2K4INDPWSMIFC","download_json":"https://pith.science/pith/NNL4WTDN4NY3U2K4INDPWSMIFC.json","view_paper":"https://pith.science/paper/NNL4WTDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.04859&json=true","fetch_graph":"https://pith.science/api/pith-number/NNL4WTDN4NY3U2K4INDPWSMIFC/graph.json","fetch_events":"https://pith.science/api/pith-number/NNL4WTDN4NY3U2K4INDPWSMIFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNL4WTDN4NY3U2K4INDPWSMIFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNL4WTDN4NY3U2K4INDPWSMIFC/action/storage_attestation","attest_author":"https://pith.science/pith/NNL4WTDN4NY3U2K4INDPWSMIFC/action/author_attestation","sign_citation":"https://pith.science/pith/NNL4WTDN4NY3U2K4INDPWSMIFC/action/citation_signature","submit_replication":"https://pith.science/pith/NNL4WTDN4NY3U2K4INDPWSMIFC/action/replication_record"}},"created_at":"2026-05-18T00:39:25.571100+00:00","updated_at":"2026-05-18T00:39:25.571100+00:00"}