{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CC7XELPLR6CQRQTDJEA5W4FN3F","short_pith_number":"pith:CC7XELPL","schema_version":"1.0","canonical_sha256":"10bf722deb8f8508c2634901db70add962b24f20fc4109e0b00637140706ff3e","source":{"kind":"arxiv","id":"1805.08315","version":4},"attestation_state":"computed","paper":{"title":"Learning long-range spatial dependencies with horizontal gated-recurrent units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Drew Linsley, Junkyung Kim, Thomas Serre, Vijay Veerabadran","submitted_at":"2018-05-21T22:52:25Z","abstract_excerpt":"Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching -- and sometimes even surpassing -- human accuracy on a variety of visual recognition tasks. Here, however, we show that these neural networks and their recent extensions struggle in recognition tasks where co-dependent visual features must be detected over long spatial ranges. We introduce the horizontal gated-recurrent unit (hGRU) to learn intrinsic horizontal connections -- both within and across"},"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":"1805.08315","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-21T22:52:25Z","cross_cats_sorted":[],"title_canon_sha256":"814663b1241c720e05e72ab56ddf789f3737afd9aacaccea3912339f811d4663","abstract_canon_sha256":"844bca6934127223d7cea3aa4d970d12c3702dcaa5116d4617112add7154be01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:43.240603Z","signature_b64":"hm0x8qWCEdyl1UvFXjBw494dv02S0bE0bI5gmjYZprgE1/fc8QZiy4GtQugQCwgh3WTEtbJw9rrVIO3Evi8mDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10bf722deb8f8508c2634901db70add962b24f20fc4109e0b00637140706ff3e","last_reissued_at":"2026-05-17T23:43:43.239888Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:43.239888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning long-range spatial dependencies with horizontal gated-recurrent units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Drew Linsley, Junkyung Kim, Thomas Serre, Vijay Veerabadran","submitted_at":"2018-05-21T22:52:25Z","abstract_excerpt":"Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching -- and sometimes even surpassing -- human accuracy on a variety of visual recognition tasks. Here, however, we show that these neural networks and their recent extensions struggle in recognition tasks where co-dependent visual features must be detected over long spatial ranges. We introduce the horizontal gated-recurrent unit (hGRU) to learn intrinsic horizontal connections -- both within and across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08315","kind":"arxiv","version":4},"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":"1805.08315","created_at":"2026-05-17T23:43:43.239980+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08315v4","created_at":"2026-05-17T23:43:43.239980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08315","created_at":"2026-05-17T23:43:43.239980+00:00"},{"alias_kind":"pith_short_12","alias_value":"CC7XELPLR6CQ","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CC7XELPLR6CQRQTD","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CC7XELPL","created_at":"2026-05-18T12:32:16.446611+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/CC7XELPLR6CQRQTDJEA5W4FN3F","json":"https://pith.science/pith/CC7XELPLR6CQRQTDJEA5W4FN3F.json","graph_json":"https://pith.science/api/pith-number/CC7XELPLR6CQRQTDJEA5W4FN3F/graph.json","events_json":"https://pith.science/api/pith-number/CC7XELPLR6CQRQTDJEA5W4FN3F/events.json","paper":"https://pith.science/paper/CC7XELPL"},"agent_actions":{"view_html":"https://pith.science/pith/CC7XELPLR6CQRQTDJEA5W4FN3F","download_json":"https://pith.science/pith/CC7XELPLR6CQRQTDJEA5W4FN3F.json","view_paper":"https://pith.science/paper/CC7XELPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08315&json=true","fetch_graph":"https://pith.science/api/pith-number/CC7XELPLR6CQRQTDJEA5W4FN3F/graph.json","fetch_events":"https://pith.science/api/pith-number/CC7XELPLR6CQRQTDJEA5W4FN3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CC7XELPLR6CQRQTDJEA5W4FN3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CC7XELPLR6CQRQTDJEA5W4FN3F/action/storage_attestation","attest_author":"https://pith.science/pith/CC7XELPLR6CQRQTDJEA5W4FN3F/action/author_attestation","sign_citation":"https://pith.science/pith/CC7XELPLR6CQRQTDJEA5W4FN3F/action/citation_signature","submit_replication":"https://pith.science/pith/CC7XELPLR6CQRQTDJEA5W4FN3F/action/replication_record"}},"created_at":"2026-05-17T23:43:43.239980+00:00","updated_at":"2026-05-17T23:43:43.239980+00:00"}