{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WDCCGLHOEL2TK5MUAIIILS4L2L","short_pith_number":"pith:WDCCGLHO","schema_version":"1.0","canonical_sha256":"b0c4232cee22f5357594021085cb8bd2d4203274d56b1106b64670f468f8320b","source":{"kind":"arxiv","id":"1707.03017","version":5},"attestation_state":"computed","paper":{"title":"Learning Visual Reasoning Without Strong Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin","submitted_at":"2017-07-10T18:49:28Z","abstract_excerpt":"Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Standard deep learning approaches tend to exploit biases in the data rather than learn this underlying structure, while leading methods learn to visually reason successfully but are hand-crafted for reasoning. We show that a general-purpose, Conditional Batch Normalization approach ac"},"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":"1707.03017","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-10T18:49:28Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"87040facafe230e7fee47045d1929c8f2ee9d34fec507381ef62cfebebd05202","abstract_canon_sha256":"10679a7c4aaaa83dc7c4482244f05011469c67f2c5ccd6e946446171cba2eb60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:46.284760Z","signature_b64":"SQM9LBdzZ05vxfDOCBJOco6qEEsBKav/J/ZFrMIZQEOWYmuCRcizAg1rSjh3Q1KuDZXGCVruZ86KM+1EGjagDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0c4232cee22f5357594021085cb8bd2d4203274d56b1106b64670f468f8320b","last_reissued_at":"2026-05-18T00:27:46.284265Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:46.284265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Visual Reasoning Without Strong Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin","submitted_at":"2017-07-10T18:49:28Z","abstract_excerpt":"Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Standard deep learning approaches tend to exploit biases in the data rather than learn this underlying structure, while leading methods learn to visually reason successfully but are hand-crafted for reasoning. We show that a general-purpose, Conditional Batch Normalization approach ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03017","kind":"arxiv","version":5},"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":"1707.03017","created_at":"2026-05-18T00:27:46.284352+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.03017v5","created_at":"2026-05-18T00:27:46.284352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03017","created_at":"2026-05-18T00:27:46.284352+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDCCGLHOEL2T","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDCCGLHOEL2TK5MU","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDCCGLHO","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.10473","citing_title":"Switchable Normalization for Learning-to-Normalize Deep Representation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10303","citing_title":"Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDCCGLHOEL2TK5MUAIIILS4L2L","json":"https://pith.science/pith/WDCCGLHOEL2TK5MUAIIILS4L2L.json","graph_json":"https://pith.science/api/pith-number/WDCCGLHOEL2TK5MUAIIILS4L2L/graph.json","events_json":"https://pith.science/api/pith-number/WDCCGLHOEL2TK5MUAIIILS4L2L/events.json","paper":"https://pith.science/paper/WDCCGLHO"},"agent_actions":{"view_html":"https://pith.science/pith/WDCCGLHOEL2TK5MUAIIILS4L2L","download_json":"https://pith.science/pith/WDCCGLHOEL2TK5MUAIIILS4L2L.json","view_paper":"https://pith.science/paper/WDCCGLHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.03017&json=true","fetch_graph":"https://pith.science/api/pith-number/WDCCGLHOEL2TK5MUAIIILS4L2L/graph.json","fetch_events":"https://pith.science/api/pith-number/WDCCGLHOEL2TK5MUAIIILS4L2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDCCGLHOEL2TK5MUAIIILS4L2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDCCGLHOEL2TK5MUAIIILS4L2L/action/storage_attestation","attest_author":"https://pith.science/pith/WDCCGLHOEL2TK5MUAIIILS4L2L/action/author_attestation","sign_citation":"https://pith.science/pith/WDCCGLHOEL2TK5MUAIIILS4L2L/action/citation_signature","submit_replication":"https://pith.science/pith/WDCCGLHOEL2TK5MUAIIILS4L2L/action/replication_record"}},"created_at":"2026-05-18T00:27:46.284352+00:00","updated_at":"2026-05-18T00:27:46.284352+00:00"}