{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:3MPQ4QDRHL5DRAY6NZYWQW7HRH","short_pith_number":"pith:3MPQ4QDR","schema_version":"1.0","canonical_sha256":"db1f0e40713afa38831e6e71685be789febc96a68ca9b7f061829a68a7784cf5","source":{"kind":"arxiv","id":"1512.02167","version":2},"attestation_state":"computed","paper":{"title":"Simple Baseline for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Arthur Szlam, Bolei Zhou, Rob Fergus, Sainbayar Sukhbaatar, Yuandong Tian","submitted_at":"2015-12-07T19:00:54Z","abstract_excerpt":"We describe a very simple bag-of-words baseline for visual question answering. This baseline concatenates the word features from the question and CNN features from the image to predict the answer. When evaluated on the challenging VQA dataset [2], it shows comparable performance to many recent approaches using recurrent neural networks. To explore the strength and weakness of the trained model, we also provide an interactive web demo and open-source code. ."},"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":"1512.02167","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-07T19:00:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9b8e65ae85411b7a6684dc95323a8b8d35897dbf573701ba342ef622661ee94e","abstract_canon_sha256":"8c7a76bc5ad9120486131d254edcec2323afa52148b55aaf0875229b221ce1eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:20.058148Z","signature_b64":"B6qBO4pF0vE2BV2mwYVPFJsrWxSotd95yDEUqB4hwv/QjJ1EMmt4NL8R5xiS6jdLPCtx3GO7Ui/RQJKZKbBECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db1f0e40713afa38831e6e71685be789febc96a68ca9b7f061829a68a7784cf5","last_reissued_at":"2026-05-18T01:24:20.057741Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:20.057741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Baseline for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Arthur Szlam, Bolei Zhou, Rob Fergus, Sainbayar Sukhbaatar, Yuandong Tian","submitted_at":"2015-12-07T19:00:54Z","abstract_excerpt":"We describe a very simple bag-of-words baseline for visual question answering. This baseline concatenates the word features from the question and CNN features from the image to predict the answer. When evaluated on the challenging VQA dataset [2], it shows comparable performance to many recent approaches using recurrent neural networks. To explore the strength and weakness of the trained model, we also provide an interactive web demo and open-source code. ."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.02167","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":"1512.02167","created_at":"2026-05-18T01:24:20.057807+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.02167v2","created_at":"2026-05-18T01:24:20.057807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.02167","created_at":"2026-05-18T01:24:20.057807+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MPQ4QDRHL5D","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MPQ4QDRHL5DRAY6","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MPQ4QDR","created_at":"2026-05-18T12:29:02.477457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10770","citing_title":"Deep Modular Co-Attention Networks for Visual Question Answering","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MPQ4QDRHL5DRAY6NZYWQW7HRH","json":"https://pith.science/pith/3MPQ4QDRHL5DRAY6NZYWQW7HRH.json","graph_json":"https://pith.science/api/pith-number/3MPQ4QDRHL5DRAY6NZYWQW7HRH/graph.json","events_json":"https://pith.science/api/pith-number/3MPQ4QDRHL5DRAY6NZYWQW7HRH/events.json","paper":"https://pith.science/paper/3MPQ4QDR"},"agent_actions":{"view_html":"https://pith.science/pith/3MPQ4QDRHL5DRAY6NZYWQW7HRH","download_json":"https://pith.science/pith/3MPQ4QDRHL5DRAY6NZYWQW7HRH.json","view_paper":"https://pith.science/paper/3MPQ4QDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.02167&json=true","fetch_graph":"https://pith.science/api/pith-number/3MPQ4QDRHL5DRAY6NZYWQW7HRH/graph.json","fetch_events":"https://pith.science/api/pith-number/3MPQ4QDRHL5DRAY6NZYWQW7HRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MPQ4QDRHL5DRAY6NZYWQW7HRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MPQ4QDRHL5DRAY6NZYWQW7HRH/action/storage_attestation","attest_author":"https://pith.science/pith/3MPQ4QDRHL5DRAY6NZYWQW7HRH/action/author_attestation","sign_citation":"https://pith.science/pith/3MPQ4QDRHL5DRAY6NZYWQW7HRH/action/citation_signature","submit_replication":"https://pith.science/pith/3MPQ4QDRHL5DRAY6NZYWQW7HRH/action/replication_record"}},"created_at":"2026-05-18T01:24:20.057807+00:00","updated_at":"2026-05-18T01:24:20.057807+00:00"}