{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5WNNN3WADSDR44CHMPEHJU46MQ","short_pith_number":"pith:5WNNN3WA","schema_version":"1.0","canonical_sha256":"ed9ad6eec01c871e704763c874d39e6411e9854e224247619725150e65341f0a","source":{"kind":"arxiv","id":"1903.02639","version":2},"attestation_state":"computed","paper":{"title":"IMEXnet: A Forward Stable Deep Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eldad Haber, Eran Treister, Keegan Lensink, Lars Ruthotto","submitted_at":"2019-03-06T22:33:06Z","abstract_excerpt":"Deep convolutional neural networks have revolutionized many machine learning and computer vision tasks, however, some remaining key challenges limit their wider use. These challenges include improving the network's robustness to perturbations of the input image and the limited ``field of view'' of convolution operators. We introduce the IMEXnet that addresses these challenges by adapting semi-implicit methods for partial differential equations. Compared to similar explicit networks, such as residual networks, our network is more stable, which has recently shown to reduce the sensitivity to sma"},"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":"1903.02639","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-06T22:33:06Z","cross_cats_sorted":[],"title_canon_sha256":"4532f0fdc53b47b2a2c7179702bb34493f83cd3798f36499108d95cb192fbf9d","abstract_canon_sha256":"4eb4380d77a8b55eab1b6c415a25e7b909bc3cdc55ca6c33eb791022e7ba4aea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:51.894233Z","signature_b64":"nuQY1wvBqnGv1DFv6/Ix6MbgdXYd/PmfijfUwsJYNBNpgxIDZ21b3Oo5NY6GWBOPTTR09FEedMn5+vfIEYG+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed9ad6eec01c871e704763c874d39e6411e9854e224247619725150e65341f0a","last_reissued_at":"2026-05-17T23:45:51.893725Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:51.893725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IMEXnet: A Forward Stable Deep Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eldad Haber, Eran Treister, Keegan Lensink, Lars Ruthotto","submitted_at":"2019-03-06T22:33:06Z","abstract_excerpt":"Deep convolutional neural networks have revolutionized many machine learning and computer vision tasks, however, some remaining key challenges limit their wider use. These challenges include improving the network's robustness to perturbations of the input image and the limited ``field of view'' of convolution operators. We introduce the IMEXnet that addresses these challenges by adapting semi-implicit methods for partial differential equations. Compared to similar explicit networks, such as residual networks, our network is more stable, which has recently shown to reduce the sensitivity to sma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02639","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":"1903.02639","created_at":"2026-05-17T23:45:51.893796+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.02639v2","created_at":"2026-05-17T23:45:51.893796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02639","created_at":"2026-05-17T23:45:51.893796+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WNNN3WADSDR","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WNNN3WADSDR44CH","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WNNN3WA","created_at":"2026-05-18T12:33:10.108867+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/5WNNN3WADSDR44CHMPEHJU46MQ","json":"https://pith.science/pith/5WNNN3WADSDR44CHMPEHJU46MQ.json","graph_json":"https://pith.science/api/pith-number/5WNNN3WADSDR44CHMPEHJU46MQ/graph.json","events_json":"https://pith.science/api/pith-number/5WNNN3WADSDR44CHMPEHJU46MQ/events.json","paper":"https://pith.science/paper/5WNNN3WA"},"agent_actions":{"view_html":"https://pith.science/pith/5WNNN3WADSDR44CHMPEHJU46MQ","download_json":"https://pith.science/pith/5WNNN3WADSDR44CHMPEHJU46MQ.json","view_paper":"https://pith.science/paper/5WNNN3WA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.02639&json=true","fetch_graph":"https://pith.science/api/pith-number/5WNNN3WADSDR44CHMPEHJU46MQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5WNNN3WADSDR44CHMPEHJU46MQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WNNN3WADSDR44CHMPEHJU46MQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WNNN3WADSDR44CHMPEHJU46MQ/action/storage_attestation","attest_author":"https://pith.science/pith/5WNNN3WADSDR44CHMPEHJU46MQ/action/author_attestation","sign_citation":"https://pith.science/pith/5WNNN3WADSDR44CHMPEHJU46MQ/action/citation_signature","submit_replication":"https://pith.science/pith/5WNNN3WADSDR44CHMPEHJU46MQ/action/replication_record"}},"created_at":"2026-05-17T23:45:51.893796+00:00","updated_at":"2026-05-17T23:45:51.893796+00:00"}