{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XF2WVBR2GCJ37UI6G7R6AC7G5X","short_pith_number":"pith:XF2WVBR2","schema_version":"1.0","canonical_sha256":"b9756a863a3093bfd11e37e3e00be6edd23e5118775da61439bf248228492065","source":{"kind":"arxiv","id":"1805.11546","version":2},"attestation_state":"computed","paper":{"title":"Like a Baby: Visually Situated Neural Language Acquisition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander G. Ororbia, Ankur Mali, David Reitter, Matthew A. Kelly","submitted_at":"2018-05-29T15:53:30Z","abstract_excerpt":"We examine the benefits of visual context in training neural language models to perform next-word prediction. A multi-modal neural architecture is introduced that outperform its equivalent trained on language alone with a 2\\% decrease in perplexity, even when no visual context is available at test. Fine-tuning the embeddings of a pre-trained state-of-the-art bidirectional language model (BERT) in the language modeling framework yields a 3.5\\% improvement. The advantage for training with visual context when testing without is robust across different languages (English, German and Spanish) and d"},"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":"1805.11546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-29T15:53:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5d62b8d1889cc7a90141738a942d1a4fdf62a3773afe65ae6a851eabae6c700","abstract_canon_sha256":"d824879cb16acf48b32b8680f9d7898fab44cf0d68982f8712176ce919b16598"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:22.634307Z","signature_b64":"H2xnxtLV15R80sz+yR9fb/GjxeFF9v/4FxQSShxqD9TRgVhdlnsXm4UGSVgl2s1LoHVHKWYQwNVChuExEih8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9756a863a3093bfd11e37e3e00be6edd23e5118775da61439bf248228492065","last_reissued_at":"2026-05-17T23:44:22.633619Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:22.633619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Like a Baby: Visually Situated Neural Language Acquisition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander G. Ororbia, Ankur Mali, David Reitter, Matthew A. Kelly","submitted_at":"2018-05-29T15:53:30Z","abstract_excerpt":"We examine the benefits of visual context in training neural language models to perform next-word prediction. A multi-modal neural architecture is introduced that outperform its equivalent trained on language alone with a 2\\% decrease in perplexity, even when no visual context is available at test. Fine-tuning the embeddings of a pre-trained state-of-the-art bidirectional language model (BERT) in the language modeling framework yields a 3.5\\% improvement. The advantage for training with visual context when testing without is robust across different languages (English, German and Spanish) and d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11546","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":"1805.11546","created_at":"2026-05-17T23:44:22.633727+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11546v2","created_at":"2026-05-17T23:44:22.633727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11546","created_at":"2026-05-17T23:44:22.633727+00:00"},{"alias_kind":"pith_short_12","alias_value":"XF2WVBR2GCJ3","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XF2WVBR2GCJ37UI6","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XF2WVBR2","created_at":"2026-05-18T12:33:01.666342+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/XF2WVBR2GCJ37UI6G7R6AC7G5X","json":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X.json","graph_json":"https://pith.science/api/pith-number/XF2WVBR2GCJ37UI6G7R6AC7G5X/graph.json","events_json":"https://pith.science/api/pith-number/XF2WVBR2GCJ37UI6G7R6AC7G5X/events.json","paper":"https://pith.science/paper/XF2WVBR2"},"agent_actions":{"view_html":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X","download_json":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X.json","view_paper":"https://pith.science/paper/XF2WVBR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11546&json=true","fetch_graph":"https://pith.science/api/pith-number/XF2WVBR2GCJ37UI6G7R6AC7G5X/graph.json","fetch_events":"https://pith.science/api/pith-number/XF2WVBR2GCJ37UI6G7R6AC7G5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/action/storage_attestation","attest_author":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/action/author_attestation","sign_citation":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/action/citation_signature","submit_replication":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/action/replication_record"}},"created_at":"2026-05-17T23:44:22.633727+00:00","updated_at":"2026-05-17T23:44:22.633727+00:00"}