{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XF2WVBR2GCJ37UI6G7R6AC7G5X","short_pith_number":"pith:XF2WVBR2","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"},"canonical_sha256":"b9756a863a3093bfd11e37e3e00be6edd23e5118775da61439bf248228492065","source":{"kind":"arxiv","id":"1805.11546","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11546","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11546v2","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11546","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"XF2WVBR2GCJ3","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XF2WVBR2GCJ37UI6","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XF2WVBR2","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XF2WVBR2GCJ37UI6G7R6AC7G5X","target":"record","payload":{"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"},"canonical_sha256":"b9756a863a3093bfd11e37e3e00be6edd23e5118775da61439bf248228492065","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"},"source_kind":"arxiv","source_id":"1805.11546","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oe2OYLi1bo19AMxXMJvzTvdF+tZMRQkQA6Uu1Ct7LZD9UCCzOHOiHucJsYcxiWEswEiggEAa7+ihym7yVTOPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:12:03.785818Z"},"content_sha256":"ddef795a4d03b3f463770682d423d26b7ebaaa2e76479d06b9395e888a22679b","schema_version":"1.0","event_id":"sha256:ddef795a4d03b3f463770682d423d26b7ebaaa2e76479d06b9395e888a22679b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XF2WVBR2GCJ37UI6G7R6AC7G5X","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Riw4WOX7QxmwZnjV1kirvswI+fQSU1FP0nVFPuw9WxYyMmqF1IjYern+LX3QNyDAhe+2pxDrvRM+hWn9p+AtBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:12:03.786256Z"},"content_sha256":"642fb609118a6c8343e76021c218d0d07c8d3c35c8cf30271f6865b33768d537","schema_version":"1.0","event_id":"sha256:642fb609118a6c8343e76021c218d0d07c8d3c35c8cf30271f6865b33768d537"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/bundle.json","state_url":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T20:12:03Z","links":{"resolver":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X","bundle":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/bundle.json","state":"https://pith.science/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XF2WVBR2GCJ37UI6G7R6AC7G5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XF2WVBR2GCJ37UI6G7R6AC7G5X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d824879cb16acf48b32b8680f9d7898fab44cf0d68982f8712176ce919b16598","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-29T15:53:30Z","title_canon_sha256":"a5d62b8d1889cc7a90141738a942d1a4fdf62a3773afe65ae6a851eabae6c700"},"schema_version":"1.0","source":{"id":"1805.11546","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11546","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11546v2","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11546","created_at":"2026-05-17T23:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"XF2WVBR2GCJ3","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XF2WVBR2GCJ37UI6","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XF2WVBR2","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:642fb609118a6c8343e76021c218d0d07c8d3c35c8cf30271f6865b33768d537","target":"graph","created_at":"2026-05-17T23:44:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Alexander G. Ororbia, Ankur Mali, David Reitter, Matthew A. Kelly","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-29T15:53:30Z","title":"Like a Baby: Visually Situated Neural Language Acquisition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11546","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ddef795a4d03b3f463770682d423d26b7ebaaa2e76479d06b9395e888a22679b","target":"record","created_at":"2026-05-17T23:44:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d824879cb16acf48b32b8680f9d7898fab44cf0d68982f8712176ce919b16598","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-29T15:53:30Z","title_canon_sha256":"a5d62b8d1889cc7a90141738a942d1a4fdf62a3773afe65ae6a851eabae6c700"},"schema_version":"1.0","source":{"id":"1805.11546","kind":"arxiv","version":2}},"canonical_sha256":"b9756a863a3093bfd11e37e3e00be6edd23e5118775da61439bf248228492065","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9756a863a3093bfd11e37e3e00be6edd23e5118775da61439bf248228492065","first_computed_at":"2026-05-17T23:44:22.633619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:22.633619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H2xnxtLV15R80sz+yR9fb/GjxeFF9v/4FxQSShxqD9TRgVhdlnsXm4UGSVgl2s1LoHVHKWYQwNVChuExEih8BQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:22.634307Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.11546","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddef795a4d03b3f463770682d423d26b7ebaaa2e76479d06b9395e888a22679b","sha256:642fb609118a6c8343e76021c218d0d07c8d3c35c8cf30271f6865b33768d537"],"state_sha256":"ac1e5d9adeee046ce59ce5e1b4400e30cbc6993f01d1193bc01a2160838362a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yrnff24ofTTXFXVM+4v8//vmejLe3YwOSy7TuKfVRNmPYeDzcKQ6MnKb2H73fbYDOG970AnRglAA3e/daYk6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T20:12:03.788899Z","bundle_sha256":"8df9aa79db1f4a86bce1c9cf6857c5cb0bd4788a363587cbbb5bfb5adfc8b59c"}}