{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:4MFC3AQPSV3Y6HCWWLC53PVOKE","short_pith_number":"pith:4MFC3AQP","schema_version":"1.0","canonical_sha256":"e30a2d820f95778f1c56b2c5ddbeae513c0595b1c770728ce3dc092b496c6552","source":{"kind":"arxiv","id":"1606.03647","version":2},"attestation_state":"computed","paper":{"title":"Training Recurrent Answering Units with Joint Loss Minimization for VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohyung Han, Hyeonwoo Noh","submitted_at":"2016-06-12T00:47:46Z","abstract_excerpt":"We propose a novel algorithm for visual question answering based on a recurrent deep neural network, where every module in the network corresponds to a complete answering unit with attention mechanism by itself. The network is optimized by minimizing loss aggregated from all the units, which share model parameters while receiving different information to compute attention probability. For training, our model attends to a region within image feature map, updates its memory based on the question and attended image feature, and answers the question based on its memory state. This procedure is per"},"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":"1606.03647","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-12T00:47:46Z","cross_cats_sorted":[],"title_canon_sha256":"79a2050b1a52bef38f451be262f6005f95b173b5332d9ad2cc69301faa0ecc76","abstract_canon_sha256":"31e1b303307d4593016f5996aa0d4123f78ffda8027ef4a6fdaef6e791aa7007"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:36.243133Z","signature_b64":"dfMxKzv4IGH5uqZNZ/tf3TIN3vIth9HZKxds010HZamaHfes1J8mmYyYIkS9VlAV9Xanj1G7NJkNZTuUqFwpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e30a2d820f95778f1c56b2c5ddbeae513c0595b1c770728ce3dc092b496c6552","last_reissued_at":"2026-05-18T01:03:36.242579Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:36.242579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Recurrent Answering Units with Joint Loss Minimization for VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohyung Han, Hyeonwoo Noh","submitted_at":"2016-06-12T00:47:46Z","abstract_excerpt":"We propose a novel algorithm for visual question answering based on a recurrent deep neural network, where every module in the network corresponds to a complete answering unit with attention mechanism by itself. The network is optimized by minimizing loss aggregated from all the units, which share model parameters while receiving different information to compute attention probability. For training, our model attends to a region within image feature map, updates its memory based on the question and attended image feature, and answers the question based on its memory state. This procedure is per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03647","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":"1606.03647","created_at":"2026-05-18T01:03:36.242646+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.03647v2","created_at":"2026-05-18T01:03:36.242646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03647","created_at":"2026-05-18T01:03:36.242646+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MFC3AQPSV3Y","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MFC3AQPSV3Y6HCW","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MFC3AQP","created_at":"2026-05-18T12:29:58.707656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15022","citing_title":"Using Large Language Models for education managements in Vietnamese with low resources","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MFC3AQPSV3Y6HCWWLC53PVOKE","json":"https://pith.science/pith/4MFC3AQPSV3Y6HCWWLC53PVOKE.json","graph_json":"https://pith.science/api/pith-number/4MFC3AQPSV3Y6HCWWLC53PVOKE/graph.json","events_json":"https://pith.science/api/pith-number/4MFC3AQPSV3Y6HCWWLC53PVOKE/events.json","paper":"https://pith.science/paper/4MFC3AQP"},"agent_actions":{"view_html":"https://pith.science/pith/4MFC3AQPSV3Y6HCWWLC53PVOKE","download_json":"https://pith.science/pith/4MFC3AQPSV3Y6HCWWLC53PVOKE.json","view_paper":"https://pith.science/paper/4MFC3AQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.03647&json=true","fetch_graph":"https://pith.science/api/pith-number/4MFC3AQPSV3Y6HCWWLC53PVOKE/graph.json","fetch_events":"https://pith.science/api/pith-number/4MFC3AQPSV3Y6HCWWLC53PVOKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MFC3AQPSV3Y6HCWWLC53PVOKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MFC3AQPSV3Y6HCWWLC53PVOKE/action/storage_attestation","attest_author":"https://pith.science/pith/4MFC3AQPSV3Y6HCWWLC53PVOKE/action/author_attestation","sign_citation":"https://pith.science/pith/4MFC3AQPSV3Y6HCWWLC53PVOKE/action/citation_signature","submit_replication":"https://pith.science/pith/4MFC3AQPSV3Y6HCWWLC53PVOKE/action/replication_record"}},"created_at":"2026-05-18T01:03:36.242646+00:00","updated_at":"2026-05-18T01:03:36.242646+00:00"}