{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:XRD27ZI3DD5ORJZE35AWNJWYSO","short_pith_number":"pith:XRD27ZI3","schema_version":"1.0","canonical_sha256":"bc47afe51b18fae8a724df4166a6d8939ad542f34dd30b63d5d8fde3c3e9ff93","source":{"kind":"arxiv","id":"1406.6247","version":1},"attestation_state":"computed","paper":{"title":"Recurrent Models of Visual Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Graves, Koray Kavukcuoglu, Nicolas Heess, Volodymyr Mnih","submitted_at":"2014-06-24T14:16:56Z","abstract_excerpt":"Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution. Like convolutional neural networks, the proposed model has a degree of translation invariance built-in, but the amount of computation it performs can be controlled independently of the input image s"},"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":"1406.6247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-24T14:16:56Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b5f82e925cfd0bb4e0c5329f474e925ced6ad4ea003a1c9b76ce2934518d6c6e","abstract_canon_sha256":"d7ed6575fcec28deb0f1504d2b4743bae5d1ef895b264ca424bda50ac0b36e24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:49:03.791792Z","signature_b64":"D084CnLqTpTWxrOW+Wl88ORksUSUxo62O9VrXkzmCdv8f1rJsN/ayuhqPOMIJZQyZTNCz5K7GOjARe7OKzxLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc47afe51b18fae8a724df4166a6d8939ad542f34dd30b63d5d8fde3c3e9ff93","last_reissued_at":"2026-05-18T02:49:03.791346Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:49:03.791346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Models of Visual Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Graves, Koray Kavukcuoglu, Nicolas Heess, Volodymyr Mnih","submitted_at":"2014-06-24T14:16:56Z","abstract_excerpt":"Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution. Like convolutional neural networks, the proposed model has a degree of translation invariance built-in, but the amount of computation it performs can be controlled independently of the input image s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.6247","kind":"arxiv","version":1},"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":"1406.6247","created_at":"2026-05-18T02:49:03.791414+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.6247v1","created_at":"2026-05-18T02:49:03.791414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.6247","created_at":"2026-05-18T02:49:03.791414+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRD27ZI3DD5O","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRD27ZI3DD5ORJZE","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRD27ZI3","created_at":"2026-05-18T12:28:57.508820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10068","citing_title":"Is It Worth the Attention? A Comparative Evaluation of Attention Layers for Argument Unit Segmentation","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO","json":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO.json","graph_json":"https://pith.science/api/pith-number/XRD27ZI3DD5ORJZE35AWNJWYSO/graph.json","events_json":"https://pith.science/api/pith-number/XRD27ZI3DD5ORJZE35AWNJWYSO/events.json","paper":"https://pith.science/paper/XRD27ZI3"},"agent_actions":{"view_html":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO","download_json":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO.json","view_paper":"https://pith.science/paper/XRD27ZI3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.6247&json=true","fetch_graph":"https://pith.science/api/pith-number/XRD27ZI3DD5ORJZE35AWNJWYSO/graph.json","fetch_events":"https://pith.science/api/pith-number/XRD27ZI3DD5ORJZE35AWNJWYSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/action/storage_attestation","attest_author":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/action/author_attestation","sign_citation":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/action/citation_signature","submit_replication":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/action/replication_record"}},"created_at":"2026-05-18T02:49:03.791414+00:00","updated_at":"2026-05-18T02:49:03.791414+00:00"}