{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:S3GPNPGDWJLSQV7H3QDWMQPFO2","short_pith_number":"pith:S3GPNPGD","schema_version":"1.0","canonical_sha256":"96ccf6bcc3b2572857e7dc076641e576b180cbb5de94723621924aef088a12a8","source":{"kind":"arxiv","id":"1509.05329","version":1},"attestation_state":"computed","paper":{"title":"Recurrent Spatial Transformer Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Casper Kaae S{\\o}nderby, Lars Maal{\\o}e, Ole Winther, S{\\o}ren Kaae S{\\o}nderby","submitted_at":"2015-09-17T16:50:29Z","abstract_excerpt":"We integrate the recently proposed spatial transformer network (SPN) [Jaderberg et. al 2015] into a recurrent neural network (RNN) to form an RNN-SPN model. We use the RNN-SPN to classify digits in cluttered MNIST sequences. The proposed model achieves a single digit error of 1.5% compared to 2.9% for a convolutional networks and 2.0% for convolutional networks with SPN layers. The SPN outputs a zoomed, rotated and skewed version of the input image. We investigate different down-sampling factors (ratio of pixel in input and output) for the SPN and show that the RNN-SPN model is able to down-sa"},"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":"1509.05329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-09-17T16:50:29Z","cross_cats_sorted":[],"title_canon_sha256":"280467bdbf6077a0520f0f6e9d627988bf7777b0b34f196e15baa479a56c6b30","abstract_canon_sha256":"4debe6c5752cc4647ddeee41c5e32a8168de994157169f41bf8b8866ed16dc2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:44.160433Z","signature_b64":"4Vu3+xgkKpHOWQPbFUtfd056mrKT1uSMCFGWe/YPR+17TxKXBR9iKp4ZW5Wm8eo/o9Ds1pKfKDcVnER03DI/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96ccf6bcc3b2572857e7dc076641e576b180cbb5de94723621924aef088a12a8","last_reissued_at":"2026-05-18T01:32:44.159965Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:44.159965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Spatial Transformer Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Casper Kaae S{\\o}nderby, Lars Maal{\\o}e, Ole Winther, S{\\o}ren Kaae S{\\o}nderby","submitted_at":"2015-09-17T16:50:29Z","abstract_excerpt":"We integrate the recently proposed spatial transformer network (SPN) [Jaderberg et. al 2015] into a recurrent neural network (RNN) to form an RNN-SPN model. We use the RNN-SPN to classify digits in cluttered MNIST sequences. The proposed model achieves a single digit error of 1.5% compared to 2.9% for a convolutional networks and 2.0% for convolutional networks with SPN layers. The SPN outputs a zoomed, rotated and skewed version of the input image. We investigate different down-sampling factors (ratio of pixel in input and output) for the SPN and show that the RNN-SPN model is able to down-sa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.05329","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":"1509.05329","created_at":"2026-05-18T01:32:44.160035+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.05329v1","created_at":"2026-05-18T01:32:44.160035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.05329","created_at":"2026-05-18T01:32:44.160035+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3GPNPGDWJLS","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3GPNPGDWJLSQV7H","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3GPNPGD","created_at":"2026-05-18T12:29:39.896362+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/S3GPNPGDWJLSQV7H3QDWMQPFO2","json":"https://pith.science/pith/S3GPNPGDWJLSQV7H3QDWMQPFO2.json","graph_json":"https://pith.science/api/pith-number/S3GPNPGDWJLSQV7H3QDWMQPFO2/graph.json","events_json":"https://pith.science/api/pith-number/S3GPNPGDWJLSQV7H3QDWMQPFO2/events.json","paper":"https://pith.science/paper/S3GPNPGD"},"agent_actions":{"view_html":"https://pith.science/pith/S3GPNPGDWJLSQV7H3QDWMQPFO2","download_json":"https://pith.science/pith/S3GPNPGDWJLSQV7H3QDWMQPFO2.json","view_paper":"https://pith.science/paper/S3GPNPGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.05329&json=true","fetch_graph":"https://pith.science/api/pith-number/S3GPNPGDWJLSQV7H3QDWMQPFO2/graph.json","fetch_events":"https://pith.science/api/pith-number/S3GPNPGDWJLSQV7H3QDWMQPFO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3GPNPGDWJLSQV7H3QDWMQPFO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3GPNPGDWJLSQV7H3QDWMQPFO2/action/storage_attestation","attest_author":"https://pith.science/pith/S3GPNPGDWJLSQV7H3QDWMQPFO2/action/author_attestation","sign_citation":"https://pith.science/pith/S3GPNPGDWJLSQV7H3QDWMQPFO2/action/citation_signature","submit_replication":"https://pith.science/pith/S3GPNPGDWJLSQV7H3QDWMQPFO2/action/replication_record"}},"created_at":"2026-05-18T01:32:44.160035+00:00","updated_at":"2026-05-18T01:32:44.160035+00:00"}