{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:3KWRQ2W7IRI2CCXJYZSMBFC4BO","short_pith_number":"pith:3KWRQ2W7","schema_version":"1.0","canonical_sha256":"daad186adf4451a10ae9c664c0945c0ba7665414937192f4193137ac0dc2d490","source":{"kind":"arxiv","id":"1605.02697","version":2},"attestation_state":"computed","paper":{"title":"Ask Your Neurons: A Deep Learning Approach to Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Marcus Rohrbach, Mario Fritz, Mateusz Malinowski","submitted_at":"2016-05-09T19:04:23Z","abstract_excerpt":"We address a question answering task on real-world images that is set up as a Visual Turing Test. By combining latest advances in image representation and natural language processing, we propose Ask Your Neurons, a scalable, jointly trained, end-to-end formulation to this problem.\n  In contrast to previous efforts, we are facing a multi-modal problem where the language output (answer) is conditioned on visual and natural language inputs (image and question). We provide additional insights into the problem by analyzing how much information is contained only in the language part for which we pro"},"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":"1605.02697","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-09T19:04:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e85c3813db40a42da646169a302ecbccf948061c507ee5ec38e110546f0afb17","abstract_canon_sha256":"3756db762195096fee93f552e2a7c4540726cc6c7d1c4775fca0f348f2cd4e2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:46.147034Z","signature_b64":"TKa0/BDPm0X/H8+5l0APspZytEhBRHjDDkH3NBaT/nXCLKNGw7UIIGfdvhjN42GTH4Qti1ZDRmfa/TP+EDJCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daad186adf4451a10ae9c664c0945c0ba7665414937192f4193137ac0dc2d490","last_reissued_at":"2026-05-18T00:56:46.146422Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:46.146422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ask Your Neurons: A Deep Learning Approach to Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Marcus Rohrbach, Mario Fritz, Mateusz Malinowski","submitted_at":"2016-05-09T19:04:23Z","abstract_excerpt":"We address a question answering task on real-world images that is set up as a Visual Turing Test. By combining latest advances in image representation and natural language processing, we propose Ask Your Neurons, a scalable, jointly trained, end-to-end formulation to this problem.\n  In contrast to previous efforts, we are facing a multi-modal problem where the language output (answer) is conditioned on visual and natural language inputs (image and question). We provide additional insights into the problem by analyzing how much information is contained only in the language part for which we pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.02697","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":"1605.02697","created_at":"2026-05-18T00:56:46.146510+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.02697v2","created_at":"2026-05-18T00:56:46.146510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.02697","created_at":"2026-05-18T00:56:46.146510+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KWRQ2W7IRI2","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KWRQ2W7IRI2CCXJ","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KWRQ2W7","created_at":"2026-05-18T12:29:55.572404+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/3KWRQ2W7IRI2CCXJYZSMBFC4BO","json":"https://pith.science/pith/3KWRQ2W7IRI2CCXJYZSMBFC4BO.json","graph_json":"https://pith.science/api/pith-number/3KWRQ2W7IRI2CCXJYZSMBFC4BO/graph.json","events_json":"https://pith.science/api/pith-number/3KWRQ2W7IRI2CCXJYZSMBFC4BO/events.json","paper":"https://pith.science/paper/3KWRQ2W7"},"agent_actions":{"view_html":"https://pith.science/pith/3KWRQ2W7IRI2CCXJYZSMBFC4BO","download_json":"https://pith.science/pith/3KWRQ2W7IRI2CCXJYZSMBFC4BO.json","view_paper":"https://pith.science/paper/3KWRQ2W7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.02697&json=true","fetch_graph":"https://pith.science/api/pith-number/3KWRQ2W7IRI2CCXJYZSMBFC4BO/graph.json","fetch_events":"https://pith.science/api/pith-number/3KWRQ2W7IRI2CCXJYZSMBFC4BO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KWRQ2W7IRI2CCXJYZSMBFC4BO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KWRQ2W7IRI2CCXJYZSMBFC4BO/action/storage_attestation","attest_author":"https://pith.science/pith/3KWRQ2W7IRI2CCXJYZSMBFC4BO/action/author_attestation","sign_citation":"https://pith.science/pith/3KWRQ2W7IRI2CCXJYZSMBFC4BO/action/citation_signature","submit_replication":"https://pith.science/pith/3KWRQ2W7IRI2CCXJYZSMBFC4BO/action/replication_record"}},"created_at":"2026-05-18T00:56:46.146510+00:00","updated_at":"2026-05-18T00:56:46.146510+00:00"}