{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YMK553VQ67BEMVRTYSXYNZTYIP","short_pith_number":"pith:YMK553VQ","schema_version":"1.0","canonical_sha256":"c315deeeb0f7c2465633c4af86e67843ea1064e824632f7493897286685efdc5","source":{"kind":"arxiv","id":"1811.00538","version":1},"attestation_state":"computed","paper":{"title":"Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander G. Schwing, Medhini Narasimhan, Svetlana Lazebnik","submitted_at":"2018-11-01T17:59:56Z","abstract_excerpt":"Accurately answering a question about a given image requires combining observations with general knowledge. While this is effortless for humans, reasoning with general knowledge remains an algorithmic challenge. To advance research in this direction a novel `fact-based' visual question answering (FVQA) task has been introduced recently along with a large set of curated facts which link two entities, i.e., two possible answers, via a relation. Given a question-image pair, deep network techniques have been employed to successively reduce the large set of facts until one of the two entities of th"},"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":"1811.00538","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-01T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"d45e95f012b0aa860ad0b15febe39cbde092b08c697c88d806f3e9185527b6f3","abstract_canon_sha256":"b1faf2c76b7ef4ef1644664d3c966e5265a397190fe3b0716073e7a29fb07635"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:44.308750Z","signature_b64":"fW9G6swFpxWOHufRCKA5ECR2w2CSemGZ7tDGH8A/bEnlVHPHLlsonjOfiUjbvsjdqnPYtDjBpMZ9dj6v8h37AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c315deeeb0f7c2465633c4af86e67843ea1064e824632f7493897286685efdc5","last_reissued_at":"2026-05-18T00:01:44.308247Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:44.308247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander G. Schwing, Medhini Narasimhan, Svetlana Lazebnik","submitted_at":"2018-11-01T17:59:56Z","abstract_excerpt":"Accurately answering a question about a given image requires combining observations with general knowledge. While this is effortless for humans, reasoning with general knowledge remains an algorithmic challenge. To advance research in this direction a novel `fact-based' visual question answering (FVQA) task has been introduced recently along with a large set of curated facts which link two entities, i.e., two possible answers, via a relation. Given a question-image pair, deep network techniques have been employed to successively reduce the large set of facts until one of the two entities of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00538","kind":"arxiv","version":1},"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":"1811.00538","created_at":"2026-05-18T00:01:44.308326+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00538v1","created_at":"2026-05-18T00:01:44.308326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00538","created_at":"2026-05-18T00:01:44.308326+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMK553VQ67BE","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMK553VQ67BEMVRT","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMK553VQ","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22933","citing_title":"Augmented Vision-Language Models: A Systematic Review","ref_index":79,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMK553VQ67BEMVRTYSXYNZTYIP","json":"https://pith.science/pith/YMK553VQ67BEMVRTYSXYNZTYIP.json","graph_json":"https://pith.science/api/pith-number/YMK553VQ67BEMVRTYSXYNZTYIP/graph.json","events_json":"https://pith.science/api/pith-number/YMK553VQ67BEMVRTYSXYNZTYIP/events.json","paper":"https://pith.science/paper/YMK553VQ"},"agent_actions":{"view_html":"https://pith.science/pith/YMK553VQ67BEMVRTYSXYNZTYIP","download_json":"https://pith.science/pith/YMK553VQ67BEMVRTYSXYNZTYIP.json","view_paper":"https://pith.science/paper/YMK553VQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00538&json=true","fetch_graph":"https://pith.science/api/pith-number/YMK553VQ67BEMVRTYSXYNZTYIP/graph.json","fetch_events":"https://pith.science/api/pith-number/YMK553VQ67BEMVRTYSXYNZTYIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMK553VQ67BEMVRTYSXYNZTYIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMK553VQ67BEMVRTYSXYNZTYIP/action/storage_attestation","attest_author":"https://pith.science/pith/YMK553VQ67BEMVRTYSXYNZTYIP/action/author_attestation","sign_citation":"https://pith.science/pith/YMK553VQ67BEMVRTYSXYNZTYIP/action/citation_signature","submit_replication":"https://pith.science/pith/YMK553VQ67BEMVRTYSXYNZTYIP/action/replication_record"}},"created_at":"2026-05-18T00:01:44.308326+00:00","updated_at":"2026-05-18T00:01:44.308326+00:00"}