{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:CHOGTO6AZ6BGGXZDACPS7FHVSA","short_pith_number":"pith:CHOGTO6A","schema_version":"1.0","canonical_sha256":"11dc69bbc0cf82635f23009f2f94f5902250d793d217c76ebda0a3945a6a9117","source":{"kind":"arxiv","id":"1511.05234","version":2},"attestation_state":"computed","paper":{"title":"Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.NE"],"primary_cat":"cs.CV","authors_text":"Huijuan Xu, Kate Saenko","submitted_at":"2015-11-17T01:00:04Z","abstract_excerpt":"We address the problem of Visual Question Answering (VQA), which requires joint image and language understanding to answer a question about a given photograph. Recent approaches have applied deep image captioning methods based on convolutional-recurrent networks to this problem, but have failed to model spatial inference. To remedy this, we propose a model we call the Spatial Memory Network and apply it to the VQA task. Memory networks are recurrent neural networks with an explicit attention mechanism that selects certain parts of the information stored in memory. Our Spatial Memory Network st"},"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":"1511.05234","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-17T01:00:04Z","cross_cats_sorted":["cs.AI","cs.CL","cs.NE"],"title_canon_sha256":"2e87dd13ac8f0027fa61ffea0059c4a056c36fe75d5ee21286bf59d6e1b1ce90","abstract_canon_sha256":"9e929e6b2a4c245bc766e97f5a57ac3d6a619a9601987e0c30b9205d28bfbe7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:18:52.365274Z","signature_b64":"SSYwPd5puuIFMDp/CWpdXttkE3bpdpPbJPxRBGA33KgA3bhqdPCajXBuOJvaWnk3QrPNJYB06c38CACXOvGJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11dc69bbc0cf82635f23009f2f94f5902250d793d217c76ebda0a3945a6a9117","last_reissued_at":"2026-05-18T01:18:52.364560Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:18:52.364560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.NE"],"primary_cat":"cs.CV","authors_text":"Huijuan Xu, Kate Saenko","submitted_at":"2015-11-17T01:00:04Z","abstract_excerpt":"We address the problem of Visual Question Answering (VQA), which requires joint image and language understanding to answer a question about a given photograph. Recent approaches have applied deep image captioning methods based on convolutional-recurrent networks to this problem, but have failed to model spatial inference. To remedy this, we propose a model we call the Spatial Memory Network and apply it to the VQA task. Memory networks are recurrent neural networks with an explicit attention mechanism that selects certain parts of the information stored in memory. Our Spatial Memory Network st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05234","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":"1511.05234","created_at":"2026-05-18T01:18:52.364666+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.05234v2","created_at":"2026-05-18T01:18:52.364666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05234","created_at":"2026-05-18T01:18:52.364666+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHOGTO6AZ6BG","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHOGTO6AZ6BGGXZD","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHOGTO6A","created_at":"2026-05-18T12:29:14.074870+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/CHOGTO6AZ6BGGXZDACPS7FHVSA","json":"https://pith.science/pith/CHOGTO6AZ6BGGXZDACPS7FHVSA.json","graph_json":"https://pith.science/api/pith-number/CHOGTO6AZ6BGGXZDACPS7FHVSA/graph.json","events_json":"https://pith.science/api/pith-number/CHOGTO6AZ6BGGXZDACPS7FHVSA/events.json","paper":"https://pith.science/paper/CHOGTO6A"},"agent_actions":{"view_html":"https://pith.science/pith/CHOGTO6AZ6BGGXZDACPS7FHVSA","download_json":"https://pith.science/pith/CHOGTO6AZ6BGGXZDACPS7FHVSA.json","view_paper":"https://pith.science/paper/CHOGTO6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.05234&json=true","fetch_graph":"https://pith.science/api/pith-number/CHOGTO6AZ6BGGXZDACPS7FHVSA/graph.json","fetch_events":"https://pith.science/api/pith-number/CHOGTO6AZ6BGGXZDACPS7FHVSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHOGTO6AZ6BGGXZDACPS7FHVSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHOGTO6AZ6BGGXZDACPS7FHVSA/action/storage_attestation","attest_author":"https://pith.science/pith/CHOGTO6AZ6BGGXZDACPS7FHVSA/action/author_attestation","sign_citation":"https://pith.science/pith/CHOGTO6AZ6BGGXZDACPS7FHVSA/action/citation_signature","submit_replication":"https://pith.science/pith/CHOGTO6AZ6BGGXZDACPS7FHVSA/action/replication_record"}},"created_at":"2026-05-18T01:18:52.364666+00:00","updated_at":"2026-05-18T01:18:52.364666+00:00"}