{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BQCI3LCNNZ5N3SQARUJEKDIXNA","short_pith_number":"pith:BQCI3LCN","schema_version":"1.0","canonical_sha256":"0c048dac4d6e7addca008d12450d17682d9f9bb87c785b828a462d37bf09d703","source":{"kind":"arxiv","id":"1810.02338","version":2},"attestation_state":"computed","paper":{"title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Antonio Torralba, Chuang Gan, Jiajun Wu, Joshua B. Tenenbaum, Kexin Yi, Pushmeet Kohli","submitted_at":"2018-10-04T17:38:50Z","abstract_excerpt":"We marry two powerful ideas: deep representation learning for visual recognition and language understanding, and symbolic program execution for reasoning. Our neural-symbolic visual question answering (NS-VQA) system first recovers a structural scene representation from the image and a program trace from the question. It then executes the program on the scene representation to obtain an answer. Incorporating symbolic structure as prior knowledge offers three unique advantages. First, executing programs on a symbolic space is more robust to long program traces; our model can solve complex reaso"},"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":"1810.02338","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-10-04T17:38:50Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"ff758e2ea9861ba87581a820c0ba0b8f2000574f5609c49ba59a790438092cb1","abstract_canon_sha256":"0fb368e823bd46a1c8c01139d46a99dbbbd4d012c58be9d87c665a24706448c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:23.045923Z","signature_b64":"1iA/KtBCf1+nEEX0T9IR0xvI2oASJdNWbRFs0ZWW6J31zSfD/vf1QYfhj+wmNsIheUrBu206Vp1xUutLN0W+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c048dac4d6e7addca008d12450d17682d9f9bb87c785b828a462d37bf09d703","last_reissued_at":"2026-05-17T23:56:23.045394Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:23.045394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Antonio Torralba, Chuang Gan, Jiajun Wu, Joshua B. Tenenbaum, Kexin Yi, Pushmeet Kohli","submitted_at":"2018-10-04T17:38:50Z","abstract_excerpt":"We marry two powerful ideas: deep representation learning for visual recognition and language understanding, and symbolic program execution for reasoning. Our neural-symbolic visual question answering (NS-VQA) system first recovers a structural scene representation from the image and a program trace from the question. It then executes the program on the scene representation to obtain an answer. Incorporating symbolic structure as prior knowledge offers three unique advantages. First, executing programs on a symbolic space is more robust to long program traces; our model can solve complex reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02338","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":"1810.02338","created_at":"2026-05-17T23:56:23.045464+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02338v2","created_at":"2026-05-17T23:56:23.045464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02338","created_at":"2026-05-17T23:56:23.045464+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQCI3LCNNZ5N","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQCI3LCNNZ5N3SQA","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQCI3LCN","created_at":"2026-05-18T12:32:16.446611+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/BQCI3LCNNZ5N3SQARUJEKDIXNA","json":"https://pith.science/pith/BQCI3LCNNZ5N3SQARUJEKDIXNA.json","graph_json":"https://pith.science/api/pith-number/BQCI3LCNNZ5N3SQARUJEKDIXNA/graph.json","events_json":"https://pith.science/api/pith-number/BQCI3LCNNZ5N3SQARUJEKDIXNA/events.json","paper":"https://pith.science/paper/BQCI3LCN"},"agent_actions":{"view_html":"https://pith.science/pith/BQCI3LCNNZ5N3SQARUJEKDIXNA","download_json":"https://pith.science/pith/BQCI3LCNNZ5N3SQARUJEKDIXNA.json","view_paper":"https://pith.science/paper/BQCI3LCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02338&json=true","fetch_graph":"https://pith.science/api/pith-number/BQCI3LCNNZ5N3SQARUJEKDIXNA/graph.json","fetch_events":"https://pith.science/api/pith-number/BQCI3LCNNZ5N3SQARUJEKDIXNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQCI3LCNNZ5N3SQARUJEKDIXNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQCI3LCNNZ5N3SQARUJEKDIXNA/action/storage_attestation","attest_author":"https://pith.science/pith/BQCI3LCNNZ5N3SQARUJEKDIXNA/action/author_attestation","sign_citation":"https://pith.science/pith/BQCI3LCNNZ5N3SQARUJEKDIXNA/action/citation_signature","submit_replication":"https://pith.science/pith/BQCI3LCNNZ5N3SQARUJEKDIXNA/action/replication_record"}},"created_at":"2026-05-17T23:56:23.045464+00:00","updated_at":"2026-05-17T23:56:23.045464+00:00"}